Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 63 results for author: <span class="mathjax">Zou, J</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/eess" aria-role="search"> Searching in archive <strong>eess</strong>. <a href="/search/?searchtype=author&query=Zou%2C+J">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Zou, J"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Zou%2C+J&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Zou, J"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zou%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zou%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zou%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.17519">arXiv:2501.17519</a> <span> [<a href="https://arxiv.org/pdf/2501.17519">pdf</a>, <a href="https://arxiv.org/format/2501.17519">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ACP/IPOC63121.2024.10809545">10.1109/ACP/IPOC63121.2024.10809545 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Low-Complexity Event Detection and Identification in Coherent Correlation OTDR Measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=M%C3%BCller%2C+J">Jasper M眉ller</a>, <a href="/search/eess?searchtype=author&query=Jovanovic%2C+O">Ognjen Jovanovic</a>, <a href="/search/eess?searchtype=author&query=Azendorf%2C+F">Florian Azendorf</a>, <a href="/search/eess?searchtype=author&query=Sandmann%2C+A">Andr茅 Sandmann</a>, <a href="/search/eess?searchtype=author&query=Ermakov%2C+R">Roman Ermakov</a>, <a href="/search/eess?searchtype=author&query=Patri%2C+S+K">Sai Kireet Patri</a>, <a href="/search/eess?searchtype=author&query=Elbers%2C+J">J枚rg-Peter Elbers</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jim Zou</a>, <a href="/search/eess?searchtype=author&query=Zibar%2C+D">Darko Zibar</a>, <a href="/search/eess?searchtype=author&query=Mas-Machuca%2C+C">Carmen Mas-Machuca</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.17519v1-abstract-short" style="display: inline;"> Pairing coherent correlation OTDR with low-complexity analysis methods, we investigate the detection of fast temperature changes and vibrations in optical fibers. A localization accuracy of ~2 m and extraction of vibration amplitudes and frequencies is demonstrated. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.17519v1-abstract-full" style="display: none;"> Pairing coherent correlation OTDR with low-complexity analysis methods, we investigate the detection of fast temperature changes and vibrations in optical fibers. A localization accuracy of ~2 m and extraction of vibration amplitudes and frequencies is demonstrated. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.17519v1-abstract-full').style.display = 'none'; document.getElementById('2501.17519v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work was supported by the ECO-eNET project with funding from the Smart Networks and Services Joint Undertaking (SNS JU) under grant agreement No. 10113933. The work has been partially funded by the Horizon Europe Framework Programme under SoFiN Project (Grant No 101093015) and Villum Foundation VI-POPCOM project (VIL54486)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.16014">arXiv:2501.16014</a> <span> [<a href="https://arxiv.org/pdf/2501.16014">pdf</a>, <a href="https://arxiv.org/format/2501.16014">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Spatial-Angular Representation Learning for High-Fidelity Continuous Super-Resolution in Diffusion MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+J">Jian Cheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+W">Wenxin Fan</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+H">Hua Guo</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+Y">Yong Liang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.16014v1-abstract-short" style="display: inline;"> Diffusion magnetic resonance imaging (dMRI) often suffers from low spatial and angular resolution due to inherent limitations in imaging hardware and system noise, adversely affecting the accurate estimation of microstructural parameters with fine anatomical details. Deep learning-based super-resolution techniques have shown promise in enhancing dMRI resolution without increasing acquisition time.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16014v1-abstract-full').style.display = 'inline'; document.getElementById('2501.16014v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.16014v1-abstract-full" style="display: none;"> Diffusion magnetic resonance imaging (dMRI) often suffers from low spatial and angular resolution due to inherent limitations in imaging hardware and system noise, adversely affecting the accurate estimation of microstructural parameters with fine anatomical details. Deep learning-based super-resolution techniques have shown promise in enhancing dMRI resolution without increasing acquisition time. However, most existing methods are confined to either spatial or angular super-resolution, limiting their effectiveness in capturing detailed microstructural features. Furthermore, traditional pixel-wise loss functions struggle to recover intricate image details essential for high-resolution reconstruction. To address these challenges, we propose SARL-dMRI, a novel Spatial-Angular Representation Learning framework for high-fidelity, continuous super-resolution in dMRI. SARL-dMRI explores implicit neural representations and spherical harmonics to model continuous spatial and angular representations, simultaneously enhancing both spatial and angular resolution while improving microstructural parameter estimation accuracy. To further preserve image fidelity, a data-fidelity module and wavelet-based frequency loss are introduced, ensuring the super-resolved images remain consistent with the original input and retain fine details. Extensive experiments demonstrate that, compared to five other state-of-the-art methods, our method significantly enhances dMRI data resolution, improves the accuracy of microstructural parameter estimation, and provides better generalization capabilities. It maintains stable performance even under a 45$\times$ downsampling factor. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.16014v1-abstract-full').style.display = 'none'; document.getElementById('2501.16014v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.13751">arXiv:2501.13751</a> <span> [<a href="https://arxiv.org/pdf/2501.13751">pdf</a>, <a href="https://arxiv.org/format/2501.13751">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> On Disentangled Training for Nonlinear Transform in Learned Image Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+H">Han Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shaohui Li</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Wenrui Dai</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+M">Maida Cao</a>, <a href="/search/eess?searchtype=author&query=Kan%2C+N">Nuowen Kan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenglin Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junni Zou</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.13751v3-abstract-short" style="display: inline;"> Learned image compression (LIC) has demonstrated superior rate-distortion (R-D) performance compared to traditional codecs, but is challenged by training inefficiency that could incur more than two weeks to train a state-of-the-art model from scratch. Existing LIC methods overlook the slow convergence caused by compacting energy in learning nonlinear transforms. In this paper, we first reveal that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13751v3-abstract-full').style.display = 'inline'; document.getElementById('2501.13751v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13751v3-abstract-full" style="display: none;"> Learned image compression (LIC) has demonstrated superior rate-distortion (R-D) performance compared to traditional codecs, but is challenged by training inefficiency that could incur more than two weeks to train a state-of-the-art model from scratch. Existing LIC methods overlook the slow convergence caused by compacting energy in learning nonlinear transforms. In this paper, we first reveal that such energy compaction consists of two components, i.e., feature decorrelation and uneven energy modulation. On such basis, we propose a linear auxiliary transform (AuxT) to disentangle energy compaction in training nonlinear transforms. The proposed AuxT obtains coarse approximation to achieve efficient energy compaction such that distribution fitting with the nonlinear transforms can be simplified to fine details. We then develop wavelet-based linear shortcuts (WLSs) for AuxT that leverages wavelet-based downsampling and orthogonal linear projection for feature decorrelation and subband-aware scaling for <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13751v3-abstract-full').style.display = 'none'; document.getElementById('2501.13751v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ICLR2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.15743">arXiv:2412.15743</a> <span> [<a href="https://arxiv.org/pdf/2412.15743">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> Coexistence Options and Performance Analysis of 100 Gbit/s Coherent PON in Brownfield DWDM Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Di+Rosa%2C+G">Gabriele Di Rosa</a>, <a href="/search/eess?searchtype=author&query=Kuipers%2C+M">Martin Kuipers</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jim Zou</a>, <a href="/search/eess?searchtype=author&query=Jovanovic%2C+O">Ognjen Jovanovic</a>, <a href="/search/eess?searchtype=author&query=Elbers%2C+J">J枚rg-Peter Elbers</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.15743v1-abstract-short" style="display: inline;"> We study system architectures for the coexistence of future coherent PON and DWDM networks. Considering deployed optical filters, we observe filtering penalties < 1dB at a laser frequency accuracy < 12GHz when using a cost-effective architecture. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15743v1-abstract-full" style="display: none;"> We study system architectures for the coexistence of future coherent PON and DWDM networks. Considering deployed optical filters, we observe filtering penalties < 1dB at a laser frequency accuracy < 12GHz when using a cost-effective architecture. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15743v1-abstract-full').style.display = 'none'; document.getElementById('2412.15743v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has been partially funded by the German Federal Ministry of Economics and Climate Action in the project Helios-KT (16IPCEI201)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14297">arXiv:2409.14297</a> <span> [<a href="https://arxiv.org/pdf/2409.14297">pdf</a>, <a href="https://arxiv.org/format/2409.14297">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> DNN-based Enhanced DOA Sensing via Massive MIMO Receiver with Switches-based Hybrid Architecture </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yifan Li</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+K">Kang Wei</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+L">Linqiong Jia</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jun Zou</a>, <a href="/search/eess?searchtype=author&query=Shu%2C+F">Feng Shu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+Y">Yaoliang Song</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiangzhou Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14297v2-abstract-short" style="display: inline;"> Switches-based hybrid architecture has attracted much attention, especially in directional-of-arrival (DOA) sensing, due to its ability of significantly reducing the hardware cost by compressing massive multiple-input multiple-output (MIMO) arrays with switching networks. However, this structure will lead to a degradation in the degrees of freedom (DOF) and accuracy of DOA estimation. To address t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14297v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14297v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14297v2-abstract-full" style="display: none;"> Switches-based hybrid architecture has attracted much attention, especially in directional-of-arrival (DOA) sensing, due to its ability of significantly reducing the hardware cost by compressing massive multiple-input multiple-output (MIMO) arrays with switching networks. However, this structure will lead to a degradation in the degrees of freedom (DOF) and accuracy of DOA estimation. To address these two issues, we first propose a switches-based sparse hybrid array (SW-SHA). In this method, we design a dynamic switching network to form a synthesized sparse array, i.e., SW-SHA, that can enlarge the virtual aperture obtained by the difference co-array, thereby significantly enhancing the DOF. Second, in order to improve the DOA estimation accuracy of switches-based hybrid arrays, a deep neural network (DNN)-based method called ASN-DNN is proposed. It includes an antenna selection network (ASN) for optimizing the switch connections based on the criterion of minimizing the Cramer-Rao lower bound (CRLB) under the peak sidelobe level (PSL) constraint and a DNN for DOA estimation. Then by integrating ASN and DNN into an iterative process, the ASN-DNN is obtained. Furthermore, the closed-form expression of CRLB for DOA estimation is derived to evaluate the performance lower bound of switches-based hybrid arrays and provide a benchmark for ASN-DNN. The simulation results show the proposed ASN-DNN can achieve a greater performance than traditional methods, especially in the low signal-to-noise ratio (SNR) regions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14297v2-abstract-full').style.display = 'none'; document.getElementById('2409.14297v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.17421">arXiv:2408.17421</a> <span> [<a href="https://arxiv.org/pdf/2408.17421">pdf</a>, <a href="https://arxiv.org/format/2408.17421">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/eess?searchtype=author&query=Jindal%2C+B">Basu Jindal</a>, <a href="/search/eess?searchtype=author&query=Alaa%2C+A">Ahmed Alaa</a>, <a href="/search/eess?searchtype=author&query=Weinreb%2C+R">Robert Weinreb</a>, <a href="/search/eess?searchtype=author&query=Wilson%2C+D">David Wilson</a>, <a href="/search/eess?searchtype=author&query=Segal%2C+E">Eran Segal</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+P">Pengtao Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.17421v1-abstract-short" style="display: inline;"> Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated segmentation masks, which are resource-intensive to produce due to the required expertise and time. This scenario often leads to ultra low-data regimes, where annotated images ar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.17421v1-abstract-full').style.display = 'inline'; document.getElementById('2408.17421v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.17421v1-abstract-full" style="display: none;"> Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated segmentation masks, which are resource-intensive to produce due to the required expertise and time. This scenario often leads to ultra low-data regimes, where annotated images are extremely limited, posing significant challenges for the generalization of conventional deep learning methods on test images. To address this, we introduce a generative deep learning framework, which uniquely generates high-quality paired segmentation masks and medical images, serving as auxiliary data for training robust models in data-scarce environments. Unlike traditional generative models that treat data generation and segmentation model training as separate processes, our method employs multi-level optimization for end-to-end data generation. This approach allows segmentation performance to directly influence the data generation process, ensuring that the generated data is specifically tailored to enhance the performance of the segmentation model. Our method demonstrated strong generalization performance across 9 diverse medical image segmentation tasks and on 16 datasets, in ultra-low data regimes, spanning various diseases, organs, and imaging modalities. When applied to various segmentation models, it achieved performance improvements of 10-20\% (absolute), in both same-domain and out-of-domain scenarios. Notably, it requires 8 to 20 times less training data than existing methods to achieve comparable results. This advancement significantly improves the feasibility and cost-effectiveness of applying deep learning in medical imaging, particularly in scenarios with limited data availability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.17421v1-abstract-full').style.display = 'none'; document.getElementById('2408.17421v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.10236">arXiv:2408.10236</a> <span> [<a href="https://arxiv.org/pdf/2408.10236">pdf</a>, <a href="https://arxiv.org/format/2408.10236">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-preserving Model-based Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Fan%2C+W">Wenxin Fan</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+J">Jian Cheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jing Yang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.10236v1-abstract-short" style="display: inline;"> Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and eddy current, leading to detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. To address this, this paper proposes a novel method, AID-DTI (\textbf{A}ccelerating h\textbf{I}gh fi\… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10236v1-abstract-full').style.display = 'inline'; document.getElementById('2408.10236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.10236v1-abstract-full" style="display: none;"> Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and eddy current, leading to detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. To address this, this paper proposes a novel method, AID-DTI (\textbf{A}ccelerating h\textbf{I}gh fi\textbf{D}elity \textbf{D}iffusion \textbf{T}ensor \textbf{I}maging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition-based regularizer, which can effectively capture fine details while suppressing noise during network training by exploiting the correlation across DTI-derived parameters. Additionally, we introduce a Nesterov-based adaptive learning algorithm that optimizes the regularization parameter dynamically to enhance the performance. AID-DTI is an extendable framework capable of incorporating flexible network architecture. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms other state-of-the-art methods both quantitatively and qualitatively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10236v1-abstract-full').style.display = 'none'; document.getElementById('2408.10236v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 3 figures, MICCAI 2024 Workshop on Computational Diffusion MRI. arXiv admin note: text overlap with arXiv:2401.01693, arXiv:2405.03159</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.04865">arXiv:2408.04865</a> <span> [<a href="https://arxiv.org/pdf/2408.04865">pdf</a>, <a href="https://arxiv.org/format/2408.04865">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> TEAdapter: Supply abundant guidance for controllable text-to-music generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jialing Zou</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+J">Jiahao Mei</a>, <a href="/search/eess?searchtype=author&query=Nan%2C+X">Xudong Nan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jinghua Li</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+D">Daoguo Dong</a>, <a href="/search/eess?searchtype=author&query=He%2C+L">Liang He</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.04865v1-abstract-short" style="display: inline;"> Although current text-guided music generation technology can cope with simple creative scenarios, achieving fine-grained control over individual text-modality conditions remains challenging as user demands become more intricate. Accordingly, we introduce the TEAcher Adapter (TEAdapter), a compact plugin designed to guide the generation process with diverse control information provided by users. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04865v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04865v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04865v1-abstract-full" style="display: none;"> Although current text-guided music generation technology can cope with simple creative scenarios, achieving fine-grained control over individual text-modality conditions remains challenging as user demands become more intricate. Accordingly, we introduce the TEAcher Adapter (TEAdapter), a compact plugin designed to guide the generation process with diverse control information provided by users. In addition, we explore the controllable generation of extended music by leveraging TEAdapter control groups trained on data of distinct structural functionalities. In general, we consider controls over global, elemental, and structural levels. Experimental results demonstrate that the proposed TEAdapter enables multiple precise controls and ensures high-quality music generation. Our module is also lightweight and transferable to any diffusion model architecture. Available code and demos will be found soon at https://github.com/Ashley1101/TEAdapter. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04865v1-abstract-full').style.display = 'none'; document.getElementById('2408.04865v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ICME'24: IEEE International Conference on Multimedia and Expo</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2024 IEEE International Conference on Multimedia and Expo (ICME 2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.18950">arXiv:2406.18950</a> <span> [<a href="https://arxiv.org/pdf/2406.18950">pdf</a>, <a href="https://arxiv.org/format/2406.18950">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> MMR-Mamba: Multi-Modal MRI Reconstruction with Mamba and Spatial-Frequency Information Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jing Zou</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Lanqing Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Q">Qi Chen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shujun Wang</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Z">Zhanli Hu</a>, <a href="/search/eess?searchtype=author&query=Xing%2C+X">Xiaohan Xing</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+J">Jing Qin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.18950v2-abstract-short" style="display: inline;"> Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the target modality, which requires longer scanning times, from under-sampled k-space data using the fully-sampled reference modality with shorter scanning times as… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18950v2-abstract-full').style.display = 'inline'; document.getElementById('2406.18950v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.18950v2-abstract-full" style="display: none;"> Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the target modality, which requires longer scanning times, from under-sampled k-space data using the fully-sampled reference modality with shorter scanning times as guidance. The primary challenge of this task is comprehensively and efficiently integrating complementary information from different modalities to achieve high-quality reconstruction. Existing methods struggle with this: 1) convolution-based models fail to capture long-range dependencies; 2) transformer-based models, while excelling in global feature modeling, struggle with quadratic computational complexity. To address this, we propose MMR-Mamba, a novel framework that thoroughly and efficiently integrates multi-modal features for MRI reconstruction, leveraging Mamba's capability to capture long-range dependencies with linear computational complexity while exploiting global properties of the Fourier domain. Specifically, we first design a Target modality-guided Cross Mamba (TCM) module in the spatial domain, which maximally restores the target modality information by selectively incorporating relevant information from the reference modality. Then, we introduce a Selective Frequency Fusion (SFF) module to efficiently integrate global information in the Fourier domain and recover high-frequency signals for the reconstruction of structural details. Furthermore, we devise an Adaptive Spatial-Frequency Fusion (ASFF) module, which mutually enhances the spatial and frequency domains by supplementing less informative channels from one domain with corresponding channels from the other. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18950v2-abstract-full').style.display = 'none'; document.getElementById('2406.18950v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 5 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.19665">arXiv:2405.19665</a> <span> [<a href="https://arxiv.org/pdf/2405.19665">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A novel fault localization with data refinement for hydroelectric units </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huang%2C+J">Jialong Huang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+J">Junlin Song</a>, <a href="/search/eess?searchtype=author&query=Lian%2C+P">Penglong Lian</a>, <a href="/search/eess?searchtype=author&query=Gan%2C+M">Mengjie Gan</a>, <a href="/search/eess?searchtype=author&query=Su%2C+Z">Zhiheng Su</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+B">Benhao Wang</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+W">Wenji Zhu</a>, <a href="/search/eess?searchtype=author&query=Pu%2C+X">Xiaomin Pu</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jianxiao Zou</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+S">Shicai Fan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.19665v1-abstract-short" style="display: inline;"> Due to the scarcity of fault samples and the complexity of non-linear and non-smooth characteristics data in hydroelectric units, most of the traditional hydroelectric unit fault localization methods are difficult to carry out accurate localization. To address these problems, a sparse autoencoder (SAE)-generative adversarial network (GAN)-wavelet noise reduction (WNR)- manifold-boosted deep learni… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19665v1-abstract-full').style.display = 'inline'; document.getElementById('2405.19665v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.19665v1-abstract-full" style="display: none;"> Due to the scarcity of fault samples and the complexity of non-linear and non-smooth characteristics data in hydroelectric units, most of the traditional hydroelectric unit fault localization methods are difficult to carry out accurate localization. To address these problems, a sparse autoencoder (SAE)-generative adversarial network (GAN)-wavelet noise reduction (WNR)- manifold-boosted deep learning (SG-WMBDL) based fault localization method for hydroelectric units is proposed. To overcome the data scarcity, a SAE is embedded into the GAN to generate more high-quality samples in the data generation module. Considering the signals involving non-linear and non-smooth characteristics, the improved WNR which combining both soft and hard thresholding and local linear embedding (LLE) are utilized to the data preprocessing module in order to reduce the noise and effectively capture the local features. In addition, to seek higher performance, the novel Adaptive Boost (AdaBoost) combined with multi deep learning is proposed to achieve accurate fault localization. The experimental results show that the SG-WMBDL can locate faults for hydroelectric units under a small number of fault samples with non-linear and non-smooth characteristics on higher precision and accuracy compared to other frontier methods, which verifies the effectiveness and practicality of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.19665v1-abstract-full').style.display = 'none'; document.getElementById('2405.19665v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6pages,4 figures,Conference on Decision and Control(CDC) conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.17766">arXiv:2405.17766</a> <span> [<a href="https://arxiv.org/pdf/2405.17766">pdf</a>, <a href="https://arxiv.org/format/2405.17766">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Thapa%2C+R">Rahul Thapa</a>, <a href="/search/eess?searchtype=author&query=He%2C+B">Bryan He</a>, <a href="/search/eess?searchtype=author&query=Kjaer%2C+M+R">Magnus Ruud Kjaer</a>, <a href="/search/eess?searchtype=author&query=Moore%2C+H">Hyatt Moore</a>, <a href="/search/eess?searchtype=author&query=Ganjoo%2C+G">Gauri Ganjoo</a>, <a href="/search/eess?searchtype=author&query=Mignot%2C+E">Emmanuel Mignot</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.17766v1-abstract-short" style="display: inline;"> Sleep is a complex physiological process evaluated through various modalities recording electrical brain, cardiac, and respiratory activities. We curate a large polysomnography dataset from over 14,000 participants comprising over 100,000 hours of multi-modal sleep recordings. Leveraging this extensive dataset, we developed SleepFM, the first multi-modal foundation model for sleep analysis. We sho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17766v1-abstract-full').style.display = 'inline'; document.getElementById('2405.17766v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.17766v1-abstract-full" style="display: none;"> Sleep is a complex physiological process evaluated through various modalities recording electrical brain, cardiac, and respiratory activities. We curate a large polysomnography dataset from over 14,000 participants comprising over 100,000 hours of multi-modal sleep recordings. Leveraging this extensive dataset, we developed SleepFM, the first multi-modal foundation model for sleep analysis. We show that a novel leave-one-out approach for contrastive learning significantly improves downstream task performance compared to representations from standard pairwise contrastive learning. A logistic regression model trained on SleepFM's learned embeddings outperforms an end-to-end trained convolutional neural network (CNN) on sleep stage classification (macro AUROC 0.88 vs 0.72 and macro AUPRC 0.72 vs 0.48) and sleep disordered breathing detection (AUROC 0.85 vs 0.69 and AUPRC 0.77 vs 0.61). Notably, the learned embeddings achieve 48% top-1 average accuracy in retrieving the corresponding recording clips of other modalities from 90,000 candidates. This work demonstrates the value of holistic multi-modal sleep modeling to fully capture the richness of sleep recordings. SleepFM is open source and available at https://github.com/rthapa84/sleepfm-codebase. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17766v1-abstract-full').style.display = 'none'; document.getElementById('2405.17766v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.05715">arXiv:2405.05715</a> <span> [<a href="https://arxiv.org/pdf/2405.05715">pdf</a>, <a href="https://arxiv.org/format/2405.05715">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Shifting the ISAC Trade-Off with Fluid Antenna Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiaqi Zou</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+H">Hao Xu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Chao Wang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lvxin Xu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songlin Sun</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+K">Kaitao Meng</a>, <a href="/search/eess?searchtype=author&query=Masouros%2C+C">Christos Masouros</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.05715v1-abstract-short" style="display: inline;"> As an emerging antenna technology, a fluid antenna system (FAS) enhances spatial diversity to improve both sensing and communication performance by shifting the active antennas among available ports. In this letter, we study the potential of shifting the integrated sensing and communication (ISAC) trade-off with FAS. We propose the model for FAS-enabled ISAC and jointly optimize the transmit beamf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05715v1-abstract-full').style.display = 'inline'; document.getElementById('2405.05715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.05715v1-abstract-full" style="display: none;"> As an emerging antenna technology, a fluid antenna system (FAS) enhances spatial diversity to improve both sensing and communication performance by shifting the active antennas among available ports. In this letter, we study the potential of shifting the integrated sensing and communication (ISAC) trade-off with FAS. We propose the model for FAS-enabled ISAC and jointly optimize the transmit beamforming and port selection of FAS. In particular, we aim to minimize the transmit power, while satisfying both communication and sensing requirements. An efficient iterative algorithm based on sparse optimization, convex approximation, and a penalty approach is developed. The simulation results show that the proposed scheme can attain 33% reductions in transmit power with guaranteed sensing and communication performance, showing the great potential of the fluid antenna for striking a flexible tradeoff between sensing and communication in ISAC systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05715v1-abstract-full').style.display = 'none'; document.getElementById('2405.05715v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03209">arXiv:2404.03209</a> <span> [<a href="https://arxiv.org/pdf/2404.03209">pdf</a>, <a href="https://arxiv.org/format/2404.03209">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+J">Jian Cheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jing Yang</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+W">Wenxin Fan</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+Y">Yong Liang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.03209v2-abstract-short" style="display: inline;"> Deep learning-based dMRI super-resolution methods can effectively enhance image resolution by leveraging the learning capabilities of neural networks on large datasets. However, these methods tend to learn a fixed scale mapping between low-resolution (LR) and high-resolution (HR) images, overlooking the need for radiologists to scale the images at arbitrary resolutions. Moreover, the pixel-wise lo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03209v2-abstract-full').style.display = 'inline'; document.getElementById('2404.03209v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03209v2-abstract-full" style="display: none;"> Deep learning-based dMRI super-resolution methods can effectively enhance image resolution by leveraging the learning capabilities of neural networks on large datasets. However, these methods tend to learn a fixed scale mapping between low-resolution (LR) and high-resolution (HR) images, overlooking the need for radiologists to scale the images at arbitrary resolutions. Moreover, the pixel-wise loss in the image domain tends to generate over-smoothed results, losing fine textures and edge information. To address these issues, we propose a novel continuous super-resolution method for dMRI, called CSR-dMRI, which utilizes an anatomical structure-assisted implicit neural representation learning approach. Specifically, the CSR-dMRI model consists of two components. The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images. The second is the implicit function network, which utilizes voxel coordinates and latent feature vectors to generate voxel intensities at corresponding positions. Additionally, a frequency-domain-based loss is introduced to preserve the structural and texture information, further enhancing the image quality. Extensive experiments on the publicly available HCP dataset validate the effectiveness of our approach. Furthermore, our method demonstrates superior generalization capability and can be applied to arbitrary-scale super-resolution, including non-integer scale factors, expanding its applicability beyond conventional approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03209v2-abstract-full').style.display = 'none'; document.getElementById('2404.03209v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.07721">arXiv:2403.07721</a> <span> [<a href="https://arxiv.org/pdf/2403.07721">pdf</a>, <a href="https://arxiv.org/format/2403.07721">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+D">Dongyang Li</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+C">Chen Wei</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shiying Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiachen Zou</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+H">Haoyang Qin</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quanying Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.07721v7-abstract-short" style="display: inline;"> How to decode human vision through neural signals has attracted a long-standing interest in neuroscience and machine learning. Modern contrastive learning and generative models improved the performance of visual decoding and reconstruction based on functional Magnetic Resonance Imaging (fMRI). However, the high cost and low temporal resolution of fMRI limit their applications in brain-computer int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07721v7-abstract-full').style.display = 'inline'; document.getElementById('2403.07721v7-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.07721v7-abstract-full" style="display: none;"> How to decode human vision through neural signals has attracted a long-standing interest in neuroscience and machine learning. Modern contrastive learning and generative models improved the performance of visual decoding and reconstruction based on functional Magnetic Resonance Imaging (fMRI). However, the high cost and low temporal resolution of fMRI limit their applications in brain-computer interfaces (BCIs), prompting a high need for visual decoding based on electroencephalography (EEG). In this study, we present an end-to-end EEG-based visual reconstruction zero-shot framework, consisting of a tailored brain encoder, called the Adaptive Thinking Mapper (ATM), which projects neural signals from different sources into the shared subspace as the clip embedding, and a two-stage multi-pipe EEG-to-image generation strategy. In stage one, EEG is embedded to align the high-level clip embedding, and then the prior diffusion model refines EEG embedding into image priors. A blurry image also decoded from EEG for maintaining the low-level feature. In stage two, we input both the high-level clip embedding, the blurry image and caption from EEG latent to a pre-trained diffusion model. Furthermore, we analyzed the impacts of different time windows and brain regions on decoding and reconstruction. The versatility of our framework is demonstrated in the magnetoencephalogram (MEG) data modality. The experimental results indicate that our EEG-based visual zero-shot framework achieves SOTA performance in classification, retrieval and reconstruction, highlighting the portability, low cost, and high temporal resolution of EEG, enabling a wide range of BCI applications. Our code is available at https://github.com/ncclab-sustech/EEG_Image_decode. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07721v7-abstract-full').style.display = 'none'; document.getElementById('2403.07721v7-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.02419">arXiv:2403.02419</a> <span> [<a href="https://arxiv.org/pdf/2403.02419">pdf</a>, <a href="https://arxiv.org/format/2403.02419">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+L">Lingjiao Chen</a>, <a href="/search/eess?searchtype=author&query=Davis%2C+J+Q">Jared Quincy Davis</a>, <a href="/search/eess?searchtype=author&query=Hanin%2C+B">Boris Hanin</a>, <a href="/search/eess?searchtype=author&query=Bailis%2C+P">Peter Bailis</a>, <a href="/search/eess?searchtype=author&query=Stoica%2C+I">Ion Stoica</a>, <a href="/search/eess?searchtype=author&query=Zaharia%2C+M">Matei Zaharia</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.02419v2-abstract-short" style="display: inline;"> Many recent state-of-the-art results in language tasks were achieved using compound systems that perform multiple Language Model (LM) calls and aggregate their responses. However, there is little understanding of how the number of LM calls - e.g., when asking the LM to answer each question multiple times and taking a majority vote - affects such a compound system's performance. In this paper, we i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02419v2-abstract-full').style.display = 'inline'; document.getElementById('2403.02419v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.02419v2-abstract-full" style="display: none;"> Many recent state-of-the-art results in language tasks were achieved using compound systems that perform multiple Language Model (LM) calls and aggregate their responses. However, there is little understanding of how the number of LM calls - e.g., when asking the LM to answer each question multiple times and taking a majority vote - affects such a compound system's performance. In this paper, we initiate the study of scaling properties of compound inference systems. We analyze, theoretically and empirically, how the number of LM calls affects the performance of Vote and Filter-Vote, two of the simplest compound system designs, which aggregate LM responses via majority voting, optionally applying LM filters. We find, surprisingly, that across multiple language tasks, the performance of both Vote and Filter-Vote can first increase but then decrease as a function of the number of LM calls. Our theoretical results suggest that this non-monotonicity is due to the diversity of query difficulties within a task: more LM calls lead to higher performance on "easy" queries, but lower performance on "hard" queries, and non-monotone behavior can emerge when a task contains both types of queries. This insight then allows us to compute, from a small number of samples, the number of LM calls that maximizes system performance, and define an analytical scaling model for both systems. Experiments show that our scaling model can accurately predict the performance of Vote and Filter-Vote systems and thus find the optimal number of LM calls to make. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02419v2-abstract-full').style.display = 'none'; document.getElementById('2403.02419v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07595">arXiv:2402.07595</a> <span> [<a href="https://arxiv.org/pdf/2402.07595">pdf</a>, <a href="https://arxiv.org/format/2402.07595">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huang%2C+Y">Yuning Huang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jingchen Zou</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+L">Lanxi Meng</a>, <a href="/search/eess?searchtype=author&query=Yue%2C+X">Xin Yue</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+Q">Qing Zhao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jianqiang Li</a>, <a href="/search/eess?searchtype=author&query=Song%2C+C">Changwei Song</a>, <a href="/search/eess?searchtype=author&query=Jimenez%2C+G">Gabriel Jimenez</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shaowu Li</a>, <a href="/search/eess?searchtype=author&query=Fu%2C+G">Guanghui Fu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.07595v2-abstract-short" style="display: inline;"> Medical image analysis frequently encounters data scarcity challenges. Transfer learning has been effective in addressing this issue while conserving computational resources. The recent advent of foundational models like the DINOv2, which uses the vision transformer architecture, has opened new opportunities in the field and gathered significant interest. However, DINOv2's performance on clinical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07595v2-abstract-full').style.display = 'inline'; document.getElementById('2402.07595v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07595v2-abstract-full" style="display: none;"> Medical image analysis frequently encounters data scarcity challenges. Transfer learning has been effective in addressing this issue while conserving computational resources. The recent advent of foundational models like the DINOv2, which uses the vision transformer architecture, has opened new opportunities in the field and gathered significant interest. However, DINOv2's performance on clinical data still needs to be verified. In this paper, we performed a glioma grading task using three clinical modalities of brain MRI data. We compared the performance of various pre-trained deep learning models, including those based on ImageNet and DINOv2, in a transfer learning context. Our focus was on understanding the impact of the freezing mechanism on performance. We also validated our findings on three other types of public datasets: chest radiography, fundus radiography, and dermoscopy. Our findings indicate that in our clinical dataset, DINOv2's performance was not as strong as ImageNet-based pre-trained models, whereas in public datasets, DINOv2 generally outperformed other models, especially when using the frozen mechanism. Similar performance was observed with various sizes of DINOv2 models across different tasks. In summary, DINOv2 is viable for medical image classification tasks, particularly with data resembling natural images. However, its effectiveness may vary with data that significantly differs from natural images such as MRI. In addition, employing smaller versions of the model can be adequate for medical task, offering resource-saving benefits. Our codes are available at https://github.com/GuanghuiFU/medical_DINOv2_eval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07595v2-abstract-full').style.display = 'none'; document.getElementById('2402.07595v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.01693">arXiv:2401.01693</a> <span> [<a href="https://arxiv.org/pdf/2401.01693">pdf</a>, <a href="https://arxiv.org/format/2401.01693">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Fan%2C+W">Wenxin Fan</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+J">Jian Cheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+X">Xinrui Ma</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jing Yang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qiegen Liu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.01693v1-abstract-short" style="display: inline;"> Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.01693v1-abstract-full').style.display = 'inline'; document.getElementById('2401.01693v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.01693v1-abstract-full" style="display: none;"> Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition (SVD)-based regularizer, which can effectively capture fine details while suppressing noise during network training. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms three state-of-the-art methods both quantitatively and qualitatively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.01693v1-abstract-full').style.display = 'none'; document.getElementById('2401.01693v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.00981">arXiv:2312.00981</a> <span> [<a href="https://arxiv.org/pdf/2312.00981">pdf</a>, <a href="https://arxiv.org/format/2312.00981">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Securing the Sensing Functionality in ISAC Networks: An Artificial Noise Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiaqi Zou</a>, <a href="/search/eess?searchtype=author&query=Masouros%2C+C">Christos Masouros</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+F">Fan Liu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songlin Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.00981v1-abstract-short" style="display: inline;"> Integrated sensing and communications (ISAC) systems employ dual-functional signals to simultaneously accomplish radar sensing and wireless communication tasks. However, ISAC systems open up new sensing security vulnerabilities to malicious illegitimate eavesdroppers (Eves) that can also exploit the transmitted waveform to extract sensing information from the environment. In this paper, we investi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00981v1-abstract-full').style.display = 'inline'; document.getElementById('2312.00981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.00981v1-abstract-full" style="display: none;"> Integrated sensing and communications (ISAC) systems employ dual-functional signals to simultaneously accomplish radar sensing and wireless communication tasks. However, ISAC systems open up new sensing security vulnerabilities to malicious illegitimate eavesdroppers (Eves) that can also exploit the transmitted waveform to extract sensing information from the environment. In this paper, we investigate the beamforming design to enhance the sensing security of an ISAC system, where the communication user (CU) serves as a sensing Eve. Our objective is to maximize the mutual information (MI) for the legitimate radar sensing receiver while considering the constraint of the MI for the Eve and the quality of service to the CUs. Then, we consider the artificial noise (AN)-aided beamforming to further enhance the sensing security. Simulation results demonstrate that our proposed methods achieve MI improvement of the legitimate receiver while limiting the sensing MI of the Eve, compared with the baseline scheme, and that the utilization of AN further contributes to sensing security. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00981v1-abstract-full').style.display = 'none'; document.getElementById('2312.00981v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.13028">arXiv:2311.13028</a> <span> [<a href="https://arxiv.org/pdf/2311.13028">pdf</a>, <a href="https://arxiv.org/format/2311.13028">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> DMLR: Data-centric Machine Learning Research -- Past, Present and Future </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Oala%2C+L">Luis Oala</a>, <a href="/search/eess?searchtype=author&query=Maskey%2C+M">Manil Maskey</a>, <a href="/search/eess?searchtype=author&query=Bat-Leah%2C+L">Lilith Bat-Leah</a>, <a href="/search/eess?searchtype=author&query=Parrish%2C+A">Alicia Parrish</a>, <a href="/search/eess?searchtype=author&query=G%C3%BCrel%2C+N+M">Nezihe Merve G眉rel</a>, <a href="/search/eess?searchtype=author&query=Kuo%2C+T">Tzu-Sheng Kuo</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/eess?searchtype=author&query=Dror%2C+R">Rotem Dror</a>, <a href="/search/eess?searchtype=author&query=Brajovic%2C+D">Danilo Brajovic</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+X">Xiaozhe Yao</a>, <a href="/search/eess?searchtype=author&query=Bartolo%2C+M">Max Bartolo</a>, <a href="/search/eess?searchtype=author&query=Rojas%2C+W+A+G">William A Gaviria Rojas</a>, <a href="/search/eess?searchtype=author&query=Hileman%2C+R">Ryan Hileman</a>, <a href="/search/eess?searchtype=author&query=Aliment%2C+R">Rainier Aliment</a>, <a href="/search/eess?searchtype=author&query=Mahoney%2C+M+W">Michael W. Mahoney</a>, <a href="/search/eess?searchtype=author&query=Risdal%2C+M">Meg Risdal</a>, <a href="/search/eess?searchtype=author&query=Lease%2C+M">Matthew Lease</a>, <a href="/search/eess?searchtype=author&query=Samek%2C+W">Wojciech Samek</a>, <a href="/search/eess?searchtype=author&query=Dutta%2C+D">Debojyoti Dutta</a>, <a href="/search/eess?searchtype=author&query=Northcutt%2C+C+G">Curtis G Northcutt</a>, <a href="/search/eess?searchtype=author&query=Coleman%2C+C">Cody Coleman</a>, <a href="/search/eess?searchtype=author&query=Hancock%2C+B">Braden Hancock</a>, <a href="/search/eess?searchtype=author&query=Koch%2C+B">Bernard Koch</a>, <a href="/search/eess?searchtype=author&query=Tadesse%2C+G+A">Girmaw Abebe Tadesse</a>, <a href="/search/eess?searchtype=author&query=Karla%C5%A1%2C+B">Bojan Karla拧</a> , et al. (13 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.13028v2-abstract-short" style="display: inline;"> Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods tow… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.13028v2-abstract-full').style.display = 'inline'; document.getElementById('2311.13028v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.13028v2-abstract-full" style="display: none;"> Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods towards positive scientific, societal and business impact. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.13028v2-abstract-full').style.display = 'none'; document.getElementById('2311.13028v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in the Journal of Data-centric Machine Learning Research (DMLR) at https://data.mlr.press/assets/pdf/v01-5.pdf</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.08758">arXiv:2311.08758</a> <span> [<a href="https://arxiv.org/pdf/2311.08758">pdf</a>, <a href="https://arxiv.org/format/2311.08758">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> A Novel Tree Model-based DNN to Achieve a High-Resolution DOA Estimation via Massive MIMO receive array </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yifan Li</a>, <a href="/search/eess?searchtype=author&query=Shu%2C+F">Feng Shu</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jun Zou</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+W">Wei Gao</a>, <a href="/search/eess?searchtype=author&query=Song%2C+Y">Yaoliang Song</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiangzhou Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.08758v4-abstract-short" style="display: inline;"> To satisfy the high-resolution requirements of direction-of-arrival (DOA) estimation, conventional deep neural network (DNN)-based methods using grid idea need to significantly increase the number of output classifications and also produce a huge high model complexity. To address this problem, a multi-level tree-based DNN model (TDNN) is proposed as an alternative, where each level takes small-sca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08758v4-abstract-full').style.display = 'inline'; document.getElementById('2311.08758v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.08758v4-abstract-full" style="display: none;"> To satisfy the high-resolution requirements of direction-of-arrival (DOA) estimation, conventional deep neural network (DNN)-based methods using grid idea need to significantly increase the number of output classifications and also produce a huge high model complexity. To address this problem, a multi-level tree-based DNN model (TDNN) is proposed as an alternative, where each level takes small-scale multi-layer neural networks (MLNNs) as nodes to divide the target angular interval into multiple sub-intervals, and each output class is associated to a MLNN at the next level. Then the number of MLNNs is gradually increasing from the first level to the last level, and so increasing the depth of tree will dramatically raise the number of output classes to improve the estimation accuracy. More importantly, this network is extended to make a multi-emitter DOA estimation. Simulation results show that the proposed TDNN performs much better than conventional DNN and root-MUSIC at extremely low signal-to-noise ratio (SNR), and can achieve Cramer-Rao lower bound (CRLB). Additionally, in the multi-emitter scenario, the proposed Q-TDNN has also made a substantial performance enhancement over DNN and Root-MUSIC, and this gain grows as the number of emitters increases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08758v4-abstract-full').style.display = 'none'; document.getElementById('2311.08758v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.16387">arXiv:2310.16387</a> <span> [<a href="https://arxiv.org/pdf/2310.16387">pdf</a>, <a href="https://arxiv.org/format/2310.16387">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Frequency-Aware Transformer for Learned Image Compression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+H">Han Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shaohui Li</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Wenrui Dai</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenglin Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junni Zou</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.16387v4-abstract-short" style="display: inline;"> Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.16387v4-abstract-full').style.display = 'inline'; document.getElementById('2310.16387v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.16387v4-abstract-full" style="display: none;"> Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency components of natural images. Additionally, we introduce frequency-modulation feed-forward network (FMFFN) to adaptively modulate different frequency components, improving rate-distortion performance. Furthermore, we present a transformer-based channel-wise autoregressive (T-CA) model that effectively exploits channel dependencies. Experiments show that our method achieves state-of-the-art rate-distortion performance compared to existing LIC methods, and evidently outperforms latest standardized codec VTM-12.1 by 14.5%, 15.1%, 13.0% in BD-rate on the Kodak, Tecnick, and CLIC datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.16387v4-abstract-full').style.display = 'none'; document.getElementById('2310.16387v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICLR2024 poster</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08415">arXiv:2309.08415</a> <span> [<a href="https://arxiv.org/pdf/2309.08415">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> </div> </div> <p class="title is-5 mathjax"> A new method of modeling the multi-stage decision-making process of CRT using machine learning with uncertainty quantification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Larsen%2C+K">Kristoffer Larsen</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+C">Chen Zhao</a>, <a href="/search/eess?searchtype=author&query=Keyak%2C+J">Joyce Keyak</a>, <a href="/search/eess?searchtype=author&query=Sha%2C+Q">Qiuying Sha</a>, <a href="/search/eess?searchtype=author&query=Paez%2C+D">Diana Paez</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xinwei Zhang</a>, <a href="/search/eess?searchtype=author&query=Hung%2C+G">Guang-Uei Hung</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiangang Zou</a>, <a href="/search/eess?searchtype=author&query=Peix%2C+A">Amalia Peix</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+W">Weihua Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.08415v4-abstract-short" style="display: inline;"> Aims. The purpose of this study is to create a multi-stage machine learning model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features fr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08415v4-abstract-full').style.display = 'inline'; document.getElementById('2309.08415v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08415v4-abstract-full" style="display: none;"> Aims. The purpose of this study is to create a multi-stage machine learning model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features from electrocardiogram (ECG) are not sufficient. Methods. 218 patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6+-1 month follow-up. A multi-stage ML model was created by combining two ensemble models: Ensemble 1 was trained with clinical variables and ECG; Ensemble 2 included Ensemble 1 plus SPECT MPI features. Uncertainty quantification from Ensemble 1 allowed for multi-stage decision-making to determine if the acquisition of SPECT data for a patient is necessary. The performance of the multi-stage model was compared with that of Ensemble models 1 and 2. Results. The response rate for CRT was 55.5% (n = 121) with overall male gender 61.0% (n = 133), an average age of 62.0+-11.8, and LVEF of 27.7+-11.0. The multi-stage model performed similarly to Ensemble 2 (which utilized the additional SPECT data) with AUC of 0.75 vs. 0.77, accuracy of 0.71 vs. 0.69, sensitivity of 0.70 vs. 0.72, and specificity 0.72 vs. 0.65, respectively. However, the multi-stage model only required SPECT MPI data for 52.7% of the patients across all folds. Conclusions. By using rule-based logic stemming from uncertainty quantification, the multi-stage model was able to reduce the need for additional SPECT MPI data acquisition without sacrificing performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08415v4-abstract-full').style.display = 'none'; document.getElementById('2309.08415v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">30 pages,6 figures. arXiv admin note: text overlap with arXiv:2305.02475</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.13995">arXiv:2308.13995</a> <span> [<a href="https://arxiv.org/pdf/2308.13995">pdf</a>, <a href="https://arxiv.org/format/2308.13995">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Generalizable Learning Reconstruction for Accelerating MR Imaging via Federated Neural Architecture Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.13995v1-abstract-short" style="display: inline;"> Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13995v1-abstract-full').style.display = 'inline'; document.getElementById('2308.13995v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.13995v1-abstract-full" style="display: none;"> Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional data for collaborative training without sharing data. However, existing federated learning MR image reconstruction methods rely on models designed manually by experts, which are complex and computational expensive, suffering from performance degradation when facing heterogeneous data distributions. In addition, these methods give inadequate consideration to fairness issues, namely, ensuring that the model's training does not introduce bias towards any specific dataset's distribution. To this end, this paper proposes a generalizable federated neural architecture search framework for accelerating MR imaging (GAutoMRI). Specifically, automatic neural architecture search is investigated for effective and efficient neural network representation learning of MR images from different centers. Furthermore, we design a fairness adjustment approach that can enable the model to learn features fairly from inconsistent distributions of different devices and centers, and thus enforce the model generalize to the unseen center. Extensive experiments show that our proposed GAutoMRI has better performances and generalization ability compared with six state-of-the-art federated learning methods. Moreover, the GAutoMRI model is significantly more lightweight, making it an efficient choice for MR image reconstruction tasks. The code will be made available at https://github.com/ternencewu123/GAutoMRI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13995v1-abstract-full').style.display = 'none'; document.getElementById('2308.13995v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.11538">arXiv:2307.11538</a> <span> [<a href="https://arxiv.org/pdf/2307.11538">pdf</a>, <a href="https://arxiv.org/format/2307.11538">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> FedAutoMRI: Federated Neural Architecture Search for MR Image Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.11538v1-abstract-short" style="display: inline;"> Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions. Federated learning, a distributed collaborative training scheme, can utilize multi-center data without the need to transfer data between institutions. However, existing federated learning MR image reconstruction methods rely on manually de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.11538v1-abstract-full').style.display = 'inline'; document.getElementById('2307.11538v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.11538v1-abstract-full" style="display: none;"> Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions. Federated learning, a distributed collaborative training scheme, can utilize multi-center data without the need to transfer data between institutions. However, existing federated learning MR image reconstruction methods rely on manually designed models which have extensive parameters and suffer from performance degradation when facing heterogeneous data distributions. To this end, this paper proposes a novel FederAted neUral archiTecture search approach fOr MR Image reconstruction (FedAutoMRI). The proposed method utilizes differentiable architecture search to automatically find the optimal network architecture. In addition, an exponential moving average method is introduced to improve the robustness of the client model to address the data heterogeneity issue. To the best of our knowledge, this is the first work to use federated neural architecture search for MR image reconstruction. Experimental results demonstrate that our proposed FedAutoMRI can achieve promising performances while utilizing a lightweight model with only a small number of model parameters compared to the classical federated learning methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.11538v1-abstract-full').style.display = 'none'; document.getElementById('2307.11538v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.04002">arXiv:2307.04002</a> <span> [<a href="https://arxiv.org/pdf/2307.04002">pdf</a>, <a href="https://arxiv.org/format/2307.04002">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Energy-Efficient Beamforming Design for Integrated Sensing and Communications Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiaqi Zou</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songlin Sun</a>, <a href="/search/eess?searchtype=author&query=Masouros%2C+C">Christos Masouros</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+Y">Yuanhao Cui</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yafeng Liu</a>, <a href="/search/eess?searchtype=author&query=Ng%2C+D+W+K">Derrick Wing Kwan Ng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.04002v1-abstract-short" style="display: inline;"> In this paper, we investigate the design of energy-efficient beamforming for an ISAC system, where the transmitted waveform is optimized for joint multi-user communication and target estimation simultaneously. We aim to maximize the system energy efficiency (EE), taking into account the constraints of a maximum transmit power budget, a minimum required signal-to-interference-plus-noise ratio (SINR… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.04002v1-abstract-full').style.display = 'inline'; document.getElementById('2307.04002v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.04002v1-abstract-full" style="display: none;"> In this paper, we investigate the design of energy-efficient beamforming for an ISAC system, where the transmitted waveform is optimized for joint multi-user communication and target estimation simultaneously. We aim to maximize the system energy efficiency (EE), taking into account the constraints of a maximum transmit power budget, a minimum required signal-to-interference-plus-noise ratio (SINR) for communication, and a maximum tolerable Cramer-Rao bound (CRB) for target estimation. We first consider communication-centric EE maximization. To handle the non-convex fractional objective function, we propose an iterative quadratic-transform-Dinkelbach method, where Schur complement and semi-definite relaxation (SDR) techniques are leveraged to solve the subproblem in each iteration. For the scenarios where sensing is critical, we propose a novel performance metric for characterizing the sensing-centric EE and optimize the metric adopted in the scenario of sensing a point-like target and an extended target. To handle the nonconvexity, we employ the successive convex approximation (SCA) technique to develop an efficient algorithm for approximating the nonconvex problem as a sequence of convex ones. Furthermore, we adopt a Pareto optimization mechanism to articulate the tradeoff between the communication-centric EE and sensing-centric EE. We formulate the search of the Pareto boundary as a constrained optimization problem and propose a computationally efficient algorithm to handle it. Numerical results validate the effectiveness of our proposed algorithms compared with the baseline schemes and the obtained approximate Pareto boundary shows that there is a non-trivial tradeoff between communication-centric EE and sensing-centric EE, where the number of communication users and EE requirements have serious effects on the achievable tradeoff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.04002v1-abstract-full').style.display = 'none'; document.getElementById('2307.04002v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01210">arXiv:2306.01210</a> <span> [<a href="https://arxiv.org/pdf/2306.01210">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> A new method using deep transfer learning on ECG to predict the response to cardiac resynchronization therapy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=He%2C+Z">Zhuo He</a>, <a href="/search/eess?searchtype=author&query=Si%2C+H">Hongjin Si</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xinwei Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Q">Qing-Hui Chen</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiangang Zou</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+W">Weihua Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.01210v1-abstract-short" style="display: inline;"> Background: Cardiac resynchronization therapy (CRT) has emerged as an effective treatment for heart failure patients with electrical dyssynchrony. However, accurately predicting which patients will respond to CRT remains a challenge. This study explores the application of deep transfer learning techniques to train a predictive model for CRT response. Methods: In this study, the short-time Fourier… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01210v1-abstract-full').style.display = 'inline'; document.getElementById('2306.01210v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01210v1-abstract-full" style="display: none;"> Background: Cardiac resynchronization therapy (CRT) has emerged as an effective treatment for heart failure patients with electrical dyssynchrony. However, accurately predicting which patients will respond to CRT remains a challenge. This study explores the application of deep transfer learning techniques to train a predictive model for CRT response. Methods: In this study, the short-time Fourier transform (STFT) technique was employed to transform ECG signals into two-dimensional images. A transfer learning approach was then applied on the MIT-BIT ECG database to pre-train a convolutional neural network (CNN) model. The model was fine-tuned to extract relevant features from the ECG images, and then tested on our dataset of CRT patients to predict their response. Results: Seventy-one CRT patients were enrolled in this study. The transfer learning model achieved an accuracy of 72% in distinguishing responders from non-responders in the local dataset. Furthermore, the model showed good sensitivity (0.78) and specificity (0.79) in identifying CRT responders. The performance of our model outperformed clinic guidelines and traditional machine learning approaches. Conclusion: The utilization of ECG images as input and leveraging the power of transfer learning allows for improved accuracy in identifying CRT responders. This approach offers potential for enhancing patient selection and improving outcomes of CRT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01210v1-abstract-full').style.display = 'none'; document.getElementById('2306.01210v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.06066">arXiv:2305.06066</a> <span> [<a href="https://arxiv.org/pdf/2305.06066">pdf</a>, <a href="https://arxiv.org/format/2305.06066">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Self-Supervised Federated Learning for Fast MR Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Pei%2C+T">Tingrui Pei</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.06066v1-abstract-short" style="display: inline;"> Federated learning (FL) based magnetic resonance (MR) image reconstruction can facilitate learning valuable priors from multi-site institutions without violating patient's privacy for accelerating MR imaging. However, existing methods rely on fully sampled data for collaborative training of the model. The client that only possesses undersampled data can neither participate in FL nor benefit from o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.06066v1-abstract-full').style.display = 'inline'; document.getElementById('2305.06066v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.06066v1-abstract-full" style="display: none;"> Federated learning (FL) based magnetic resonance (MR) image reconstruction can facilitate learning valuable priors from multi-site institutions without violating patient's privacy for accelerating MR imaging. However, existing methods rely on fully sampled data for collaborative training of the model. The client that only possesses undersampled data can neither participate in FL nor benefit from other clients. Furthermore, heterogeneous data distributions hinder FL from training an effective deep learning reconstruction model and thus cause performance degradation. To address these issues, we propose a Self-Supervised Federated Learning method (SSFedMRI). SSFedMRI explores the physics-based contrastive reconstruction networks in each client to realize cross-site collaborative training in the absence of fully sampled data. Furthermore, a personalized soft update scheme is designed to simultaneously capture the global shared representations among different centers and maintain the specific data distribution of each client. The proposed method is evaluated on four datasets and compared to the latest state-of-the-art approaches. Experimental results demonstrate that SSFedMRI possesses strong capability in reconstructing accurate MR images both visually and quantitatively on both in-distribution and out-of-distribution datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.06066v1-abstract-full').style.display = 'none'; document.getElementById('2305.06066v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages,4 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.00650">arXiv:2305.00650</a> <span> [<a href="https://arxiv.org/pdf/2305.00650">pdf</a>, <a href="https://arxiv.org/format/2305.00650">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Discover and Cure: Concept-aware Mitigation of Spurious Correlation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+S">Shirley Wu</a>, <a href="/search/eess?searchtype=author&query=Yuksekgonul%2C+M">Mert Yuksekgonul</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Linjun Zhang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.00650v2-abstract-short" style="display: inline;"> Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats with bed backgrounds can fail to predict the existence of cats in other environments without beds. Mitigating spurious correlations is crucial in building trustworthy models. However, the existing works lack transparency t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00650v2-abstract-full').style.display = 'inline'; document.getElementById('2305.00650v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.00650v2-abstract-full" style="display: none;"> Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats with bed backgrounds can fail to predict the existence of cats in other environments without beds. Mitigating spurious correlations is crucial in building trustworthy models. However, the existing works lack transparency to offer insights into the mitigation process. In this work, we propose an interpretable framework, Discover and Cure (DISC), to tackle the issue. With human-interpretable concepts, DISC iteratively 1) discovers unstable concepts across different environments as spurious attributes, then 2) intervenes on the training data using the discovered concepts to reduce spurious correlation. Across systematic experiments, DISC provides superior generalization ability and interpretability than the existing approaches. Specifically, it outperforms the state-of-the-art methods on an object recognition task and a skin-lesion classification task by 7.5% and 9.6%, respectively. Additionally, we offer theoretical analysis and guarantees to understand the benefits of models trained by DISC. Code and data are available at https://github.com/Wuyxin/DISC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00650v2-abstract-full').style.display = 'none'; document.getElementById('2305.00650v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICML 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.00250">arXiv:2305.00250</a> <span> [<a href="https://arxiv.org/pdf/2305.00250">pdf</a>, <a href="https://arxiv.org/format/2305.00250">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</span> </div> </div> <p class="title is-5 mathjax"> A Direct Sampling-Based Deep Learning Approach for Inverse Medium Scattering Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ning%2C+J">Jianfeng Ning</a>, <a href="/search/eess?searchtype=author&query=Han%2C+F">Fuqun Han</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jun Zou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.00250v1-abstract-short" style="display: inline;"> In this work, we focus on the inverse medium scattering problem (IMSP), which aims to recover unknown scatterers based on measured scattered data. Motivated by the efficient direct sampling method (DSM) introduced in [23], we propose a novel direct sampling-based deep learning approach (DSM-DL)for reconstructing inhomogeneous scatterers. In particular, we use the U-Net neural network to learn the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00250v1-abstract-full').style.display = 'inline'; document.getElementById('2305.00250v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.00250v1-abstract-full" style="display: none;"> In this work, we focus on the inverse medium scattering problem (IMSP), which aims to recover unknown scatterers based on measured scattered data. Motivated by the efficient direct sampling method (DSM) introduced in [23], we propose a novel direct sampling-based deep learning approach (DSM-DL)for reconstructing inhomogeneous scatterers. In particular, we use the U-Net neural network to learn the relation between the index functions and the true contrasts. Our proposed DSM-DL is computationally efficient, robust to noise, easy to implement, and able to naturally incorporate multiple measured data to achieve high-quality reconstructions. Some representative tests are carried out with varying numbers of incident waves and different noise levels to evaluate the performance of the proposed method. The results demonstrate the promising benefits of combining deep learning techniques with the DSM for IMSP. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00250v1-abstract-full').style.display = 'none'; document.getElementById('2305.00250v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.00179">arXiv:2305.00179</a> <span> [<a href="https://arxiv.org/pdf/2305.00179">pdf</a>, <a href="https://arxiv.org/format/2305.00179">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Integrated Sensing and Communications: Recent Advances and Ten Open Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lu%2C+S">Shihang Lu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+F">Fan Liu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yunxin Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+K">Kecheng Zhang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+H">Hongjia Huang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiaqi Zou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xinyu Li</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Y">Yuxiang Dong</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+F">Fuwang Dong</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+J">Jia Zhu</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+Y">Yifeng Xiong</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+W">Weijie Yuan</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+Y">Yuanhao Cui</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.00179v2-abstract-short" style="display: inline;"> It is anticipated that integrated sensing and communications (ISAC) would be one of the key enablers of next-generation wireless networks (such as beyond 5G (B5G) and 6G) for supporting a variety of emerging applications. In this paper, we provide a comprehensive review of the recent advances in ISAC systems, with a particular focus on their foundations, system design, networking aspects and ISAC… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00179v2-abstract-full').style.display = 'inline'; document.getElementById('2305.00179v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.00179v2-abstract-full" style="display: none;"> It is anticipated that integrated sensing and communications (ISAC) would be one of the key enablers of next-generation wireless networks (such as beyond 5G (B5G) and 6G) for supporting a variety of emerging applications. In this paper, we provide a comprehensive review of the recent advances in ISAC systems, with a particular focus on their foundations, system design, networking aspects and ISAC applications. Furthermore, we discuss the corresponding open questions of the above that emerged in each issue. Hence, we commence with the information theory of sensing and communications (S$\&$C), followed by the information-theoretic limits of ISAC systems by shedding light on the fundamental performance metrics. Next, we discuss their clock synchronization and phase offset problems, the associated Pareto-optimal signaling strategies, as well as the associated super-resolution ISAC system design. Moreover, we envision that ISAC ushers in a paradigm shift for the future cellular networks relying on network sensing, transforming the classic cellular architecture, cross-layer resource management methods, and transmission protocols. In ISAC applications, we further highlight the security and privacy issues of wireless sensing. Finally, we close by studying the recent advances in a representative ISAC use case, namely the multi-object multi-task (MOMT) recognition problem using wireless signals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.00179v2-abstract-full').style.display = 'none'; document.getElementById('2305.00179v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">26 pages, 22 figures, resubmitted to IEEE Journal. Appreciation for the outstanding contributions of coauthors in the paper!</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.07502">arXiv:2304.07502</a> <span> [<a href="https://arxiv.org/pdf/2304.07502">pdf</a>, <a href="https://arxiv.org/format/2304.07502">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Model-based Federated Learning for Accurate MR Image Reconstruction from Undersampled k-space Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qiegen Liu</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.07502v1-abstract-short" style="display: inline;"> Deep learning-based methods have achieved encouraging performances in the field of magnetic resonance (MR) image reconstruction. Nevertheless, to properly learn a powerful and robust model, these methods generally require large quantities of data, the collection of which from multiple centers may cause ethical and data privacy violation issues. Lately, federated learning has served as a promising… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.07502v1-abstract-full').style.display = 'inline'; document.getElementById('2304.07502v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.07502v1-abstract-full" style="display: none;"> Deep learning-based methods have achieved encouraging performances in the field of magnetic resonance (MR) image reconstruction. Nevertheless, to properly learn a powerful and robust model, these methods generally require large quantities of data, the collection of which from multiple centers may cause ethical and data privacy violation issues. Lately, federated learning has served as a promising solution to exploit multi-center data while getting rid of the data transfer between institutions. However, high heterogeneity exists in the data from different centers, and existing federated learning methods tend to use average aggregation methods to combine the client's information, which limits the performance and generalization capability of the trained models. In this paper, we propose a Model-based Federated learning framework (ModFed). ModFed has three major contributions: 1) Different from the existing data-driven federated learning methods, model-driven neural networks are designed to relieve each client's dependency on large data; 2) An adaptive dynamic aggregation scheme is proposed to address the data heterogeneity issue and improve the generalization capability and robustness the trained neural network models; 3) A spatial Laplacian attention mechanism and a personalized client-side loss regularization are introduced to capture the detailed information for accurate image reconstruction. ModFed is evaluated on three in-vivo datasets. Experimental results show that ModFed has strong capability in improving image reconstruction quality and enforcing model generalization capability when compared to the other five state-of-the-art federated learning approaches. Codes will be made available at https://github.com/ternencewu123/ModFed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.07502v1-abstract-full').style.display = 'none'; document.getElementById('2304.07502v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.08113">arXiv:2303.08113</a> <span> [<a href="https://arxiv.org/pdf/2303.08113">pdf</a>, <a href="https://arxiv.org/format/2303.08113">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Learning Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jing Zou</a>, <a href="/search/eess?searchtype=author&query=Debroux%2C+N">No茅mie Debroux</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Lihao Liu</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+J">Jing Qin</a>, <a href="/search/eess?searchtype=author&query=Sch%C3%B6nlieb%2C+C">Carola-Bibiane Sch枚nlieb</a>, <a href="/search/eess?searchtype=author&query=Aviles-Rivero%2C+A+I">Angelica I Aviles-Rivero</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.08113v2-abstract-short" style="display: inline;"> Deformable image registration is a fundamental task in medical image analysis and plays a crucial role in a wide range of clinical applications. Recently, deep learning-based approaches have been widely studied for deformable medical image registration and achieved promising results. However, existing deep learning image registration techniques do not theoretically guarantee topology-preserving tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.08113v2-abstract-full').style.display = 'inline'; document.getElementById('2303.08113v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.08113v2-abstract-full" style="display: none;"> Deformable image registration is a fundamental task in medical image analysis and plays a crucial role in a wide range of clinical applications. Recently, deep learning-based approaches have been widely studied for deformable medical image registration and achieved promising results. However, existing deep learning image registration techniques do not theoretically guarantee topology-preserving transformations. This is a key property to preserve anatomical structures and achieve plausible transformations that can be used in real clinical settings. We propose a novel framework for deformable image registration. Firstly, we introduce a novel regulariser based on conformal-invariant properties in a nonlinear elasticity setting. Our regulariser enforces the deformation field to be smooth, invertible and orientation-preserving. More importantly, we strictly guarantee topology preservation yielding to a clinical meaningful registration. Secondly, we boost the performance of our regulariser through coordinate MLPs, where one can view the to-be-registered images as continuously differentiable entities. We demonstrate, through numerical and visual experiments, that our framework is able to outperform current techniques for image registration. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.08113v2-abstract-full').style.display = 'none'; document.getElementById('2303.08113v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.02666">arXiv:2303.02666</a> <span> [<a href="https://arxiv.org/pdf/2303.02666">pdf</a>, <a href="https://arxiv.org/format/2303.02666">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learned Lossless Compression for JPEG via Frequency-Domain Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Luo%2C+J">Jixiang Luo</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shaohui Li</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Wenrui Dai</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenglin Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junni Zou</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.02666v1-abstract-short" style="display: inline;"> JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end opti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.02666v1-abstract-full').style.display = 'inline'; document.getElementById('2303.02666v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.02666v1-abstract-full" style="display: none;"> JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An autoencoder-like architecture is designed based on the weight-shared blocks to realize entropy modeling of grouped DCT coefficients and independently compress the priors. We attempt to realize learned lossless compression of JPEG images in the frequency domain. Experimental results demonstrate that the proposed framework achieves superior or comparable performance in comparison to most recent lossless compressors with handcrafted context modeling for JPEG images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.02666v1-abstract-full').style.display = 'none'; document.getElementById('2303.02666v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.05898">arXiv:2301.05898</a> <span> [<a href="https://arxiv.org/pdf/2301.05898">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.neubiorev.2023.105111">10.1016/j.neubiorev.2023.105111 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Acoustic correlates of the syllabic rhythm of speech: Modulation spectrum or local features of the temporal envelope </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yuran Zhang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiajie Zou</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+N">Nai Ding</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.05898v1-abstract-short" style="display: inline;"> The syllable is a perceptually salient unit in speech. Since both the syllable and its acoustic correlate, i.e., the speech envelope, have a preferred range of rhythmicity between 4 and 8 Hz, it is hypothesized that theta-band neural oscillations play a major role in extracting syllables based on the envelope. A literature survey, however, reveals inconsistent evidence about the relationship betwe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.05898v1-abstract-full').style.display = 'inline'; document.getElementById('2301.05898v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.05898v1-abstract-full" style="display: none;"> The syllable is a perceptually salient unit in speech. Since both the syllable and its acoustic correlate, i.e., the speech envelope, have a preferred range of rhythmicity between 4 and 8 Hz, it is hypothesized that theta-band neural oscillations play a major role in extracting syllables based on the envelope. A literature survey, however, reveals inconsistent evidence about the relationship between speech envelope and syllables, and the current study revisits this question by analyzing large speech corpora. It is shown that the center frequency of speech envelope, characterized by the modulation spectrum, reliably correlates with the rate of syllables only when the analysis is pooled over minutes of speech recordings. In contrast, in the time domain, a component of the speech envelope is reliably phase-locked to syllable onsets. Based on a speaker-independent model, the timing of syllable onsets explains about 24% variance of the speech envelope. These results indicate that local features in the speech envelope, instead of the modulation spectrum, are a more reliable acoustic correlate of syllables. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.05898v1-abstract-full').style.display = 'none'; document.getElementById('2301.05898v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2212.12134">arXiv:2212.12134</a> <span> [<a href="https://arxiv.org/pdf/2212.12134">pdf</a>, <a href="https://arxiv.org/format/2212.12134">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> AMDET: Attention based Multiple Dimensions EEG Transformer for Emotion Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yongling Xu</a>, <a href="/search/eess?searchtype=author&query=Du%2C+Y">Yang Du</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jing Zou</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+T">Tianying Zhou</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+L">Lushan Xiao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Li Liu</a>, <a href="/search/eess?searchtype=author&query=Pengcheng"> Pengcheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2212.12134v1-abstract-short" style="display: inline;"> Affective computing is an important branch of artificial intelligence, and with the rapid development of brain computer interface technology, emotion recognition based on EEG signals has received broad attention. It is still a great challenge to effectively explore the multi-dimensional information in the EEG data in spite of a large number of deep learning methods. In this paper, we propose a dee… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.12134v1-abstract-full').style.display = 'inline'; document.getElementById('2212.12134v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.12134v1-abstract-full" style="display: none;"> Affective computing is an important branch of artificial intelligence, and with the rapid development of brain computer interface technology, emotion recognition based on EEG signals has received broad attention. It is still a great challenge to effectively explore the multi-dimensional information in the EEG data in spite of a large number of deep learning methods. In this paper, we propose a deep model called Attention-based Multiple Dimensions EEG Transformer (AMDET), which can exploit the complementarity among the spectral-spatial-temporal features of EEG data by employing the multi-dimensional global attention mechanism. We transformed the original EEG data into 3D temporal-spectral-spatial representations and then the AMDET would use spectral-spatial transformer encoder layer to extract effective features in the EEG signal and concentrate on the critical time frame with a temporal attention layer. We conduct extensive experiments on the DEAP, SEED, and SEED-IV datasets to evaluate the performance of AMDET and the results outperform the state-of-the-art baseline on three datasets. Accuracy rates of 97.48%, 96.85%, 97.17%, 87.32% were achieved in the DEAP-Arousal, DEAP-Valence, SEED, and SEED-IV datasets, respectively. We also conduct extensive experiments to explore the possible brain regions that influence emotions and the coupling of EEG signals. AMDET can perform as well even with few channels which are identified by visualizing what learned model focus on. The accuracy could achieve over 90% even with only eight channels and it is of great use and benefit for practical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.12134v1-abstract-full').style.display = 'none'; document.getElementById('2212.12134v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.13440">arXiv:2211.13440</a> <span> [<a href="https://arxiv.org/pdf/2211.13440">pdf</a>, <a href="https://arxiv.org/format/2211.13440">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Iterative Data Refinement for Self-Supervised MR Image Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+X">Xue Liu</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+X">Xiawu Zheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.13440v1-abstract-short" style="display: inline;"> Magnetic Resonance Imaging (MRI) has become an important technique in the clinic for the visualization, detection, and diagnosis of various diseases. However, one bottleneck limitation of MRI is the relatively slow data acquisition process. Fast MRI based on k-space undersampling and high-quality image reconstruction has been widely utilized, and many deep learning-based methods have been develope… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13440v1-abstract-full').style.display = 'inline'; document.getElementById('2211.13440v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.13440v1-abstract-full" style="display: none;"> Magnetic Resonance Imaging (MRI) has become an important technique in the clinic for the visualization, detection, and diagnosis of various diseases. However, one bottleneck limitation of MRI is the relatively slow data acquisition process. Fast MRI based on k-space undersampling and high-quality image reconstruction has been widely utilized, and many deep learning-based methods have been developed in recent years. Although promising results have been achieved, most existing methods require fully-sampled reference data for training the deep learning models. Unfortunately, fully-sampled MRI data are difficult if not impossible to obtain in real-world applications. To address this issue, we propose a data refinement framework for self-supervised MR image reconstruction. Specifically, we first analyze the reason of the performance gap between self-supervised and supervised methods and identify that the bias in the training datasets between the two is one major factor. Then, we design an effective self-supervised training data refinement method to reduce this data bias. With the data refinement, an enhanced self-supervised MR image reconstruction framework is developed to prompt accurate MR imaging. We evaluate our method on an in-vivo MRI dataset. Experimental results show that without utilizing any fully sampled MRI data, our self-supervised framework possesses strong capabilities in capturing image details and structures at high acceleration factors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13440v1-abstract-full').style.display = 'none'; document.getElementById('2211.13440v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 2 figures, 1 table</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T10 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.09105">arXiv:2209.09105</a> <span> [<a href="https://arxiv.org/pdf/2209.09105">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Development and Clinical Evaluation of an AI Support Tool for Improving Telemedicine Photo Quality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Vodrahalli%2C+K">Kailas Vodrahalli</a>, <a href="/search/eess?searchtype=author&query=Ko%2C+J">Justin Ko</a>, <a href="/search/eess?searchtype=author&query=Chiou%2C+A+S">Albert S. Chiou</a>, <a href="/search/eess?searchtype=author&query=Novoa%2C+R">Roberto Novoa</a>, <a href="/search/eess?searchtype=author&query=Abid%2C+A">Abubakar Abid</a>, <a href="/search/eess?searchtype=author&query=Phung%2C+M">Michelle Phung</a>, <a href="/search/eess?searchtype=author&query=Yekrang%2C+K">Kiana Yekrang</a>, <a href="/search/eess?searchtype=author&query=Petrone%2C+P">Paige Petrone</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a>, <a href="/search/eess?searchtype=author&query=Daneshjou%2C+R">Roxana Daneshjou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2209.09105v1-abstract-short" style="display: inline;"> Telemedicine utilization was accelerated during the COVID-19 pandemic, and skin conditions were a common use case. However, the quality of photographs sent by patients remains a major limitation. To address this issue, we developed TrueImage 2.0, an artificial intelligence (AI) model for assessing patient photo quality for telemedicine and providing real-time feedback to patients for photo quality… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09105v1-abstract-full').style.display = 'inline'; document.getElementById('2209.09105v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.09105v1-abstract-full" style="display: none;"> Telemedicine utilization was accelerated during the COVID-19 pandemic, and skin conditions were a common use case. However, the quality of photographs sent by patients remains a major limitation. To address this issue, we developed TrueImage 2.0, an artificial intelligence (AI) model for assessing patient photo quality for telemedicine and providing real-time feedback to patients for photo quality improvement. TrueImage 2.0 was trained on 1700 telemedicine images annotated by clinicians for photo quality. On a retrospective dataset of 357 telemedicine images, TrueImage 2.0 effectively identified poor quality images (Receiver operator curve area under the curve (ROC-AUC) =0.78) and the reason for poor quality (Blurry ROC-AUC=0.84, Lighting issues ROC-AUC=0.70). The performance is consistent across age, gender, and skin tone. Next, we assessed whether patient-TrueImage 2.0 interaction led to an improvement in submitted photo quality through a prospective clinical pilot study with 98 patients. TrueImage 2.0 reduced the number of patients with a poor-quality image by 68.0%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.09105v1-abstract-full').style.display = 'none'; document.getElementById('2209.09105v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">24 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.03904">arXiv:2208.03904</a> <span> [<a href="https://arxiv.org/pdf/2208.03904">pdf</a>, <a href="https://arxiv.org/format/2208.03904">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+S">Sen Jia</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Pei%2C+T">Tingrui Pei</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2208.03904v1-abstract-short" style="display: inline;"> Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (S… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.03904v1-abstract-full').style.display = 'inline'; document.getElementById('2208.03904v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.03904v1-abstract-full" style="display: none;"> Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data. The proposed framework is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a specially designed co-training loss. The framework is flexible to be integrated with both data-driven networks and model-based iterative un-rolled networks. Our method has been evaluated on in-vivo dataset and compared it to four state-of-the-art methods. Results show that our method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.03904v1-abstract-full').style.display = 'none'; document.getElementById('2208.03904v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages,9 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.03242">arXiv:2205.03242</a> <span> [<a href="https://arxiv.org/pdf/2205.03242">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Electrocardiographic Deep Learning for Predicting Post-Procedural Mortality </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ouyang%2C+D">David Ouyang</a>, <a href="/search/eess?searchtype=author&query=Theurer%2C+J">John Theurer</a>, <a href="/search/eess?searchtype=author&query=Stein%2C+N+R">Nathan R. Stein</a>, <a href="/search/eess?searchtype=author&query=Hughes%2C+J+W">J. Weston Hughes</a>, <a href="/search/eess?searchtype=author&query=Elias%2C+P">Pierre Elias</a>, <a href="/search/eess?searchtype=author&query=He%2C+B">Bryan He</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+N">Neal Yuan</a>, <a href="/search/eess?searchtype=author&query=Duffy%2C+G">Grant Duffy</a>, <a href="/search/eess?searchtype=author&query=Sandhu%2C+R+K">Roopinder K. Sandhu</a>, <a href="/search/eess?searchtype=author&query=Ebinger%2C+J">Joseph Ebinger</a>, <a href="/search/eess?searchtype=author&query=Botting%2C+P">Patrick Botting</a>, <a href="/search/eess?searchtype=author&query=Jujjavarapu%2C+M">Melvin Jujjavarapu</a>, <a href="/search/eess?searchtype=author&query=Claggett%2C+B">Brian Claggett</a>, <a href="/search/eess?searchtype=author&query=Tooley%2C+J+E">James E. Tooley</a>, <a href="/search/eess?searchtype=author&query=Poterucha%2C+T">Tim Poterucha</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J+H">Jonathan H. Chen</a>, <a href="/search/eess?searchtype=author&query=Nurok%2C+M">Michael Nurok</a>, <a href="/search/eess?searchtype=author&query=Perez%2C+M">Marco Perez</a>, <a href="/search/eess?searchtype=author&query=Perotte%2C+A">Adler Perotte</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J+Y">James Y. Zou</a>, <a href="/search/eess?searchtype=author&query=Cook%2C+N+R">Nancy R. Cook</a>, <a href="/search/eess?searchtype=author&query=Chugh%2C+S+S">Sumeet S. Chugh</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+S">Susan Cheng</a>, <a href="/search/eess?searchtype=author&query=Albert%2C+C+M">Christine M. Albert</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.03242v1-abstract-short" style="display: inline;"> Background. Pre-operative risk assessments used in clinical practice are limited in their ability to identify risk for post-operative mortality. We hypothesize that electrocardiograms contain hidden risk markers that can help prognosticate post-operative mortality. Methods. In a derivation cohort of 45,969 pre-operative patients (age 59+- 19 years, 55 percent women), a deep learning algorithm was… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.03242v1-abstract-full').style.display = 'inline'; document.getElementById('2205.03242v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.03242v1-abstract-full" style="display: none;"> Background. Pre-operative risk assessments used in clinical practice are limited in their ability to identify risk for post-operative mortality. We hypothesize that electrocardiograms contain hidden risk markers that can help prognosticate post-operative mortality. Methods. In a derivation cohort of 45,969 pre-operative patients (age 59+- 19 years, 55 percent women), a deep learning algorithm was developed to leverage waveform signals from pre-operative ECGs to discriminate post-operative mortality. Model performance was assessed in a holdout internal test dataset and in two external hospital cohorts and compared with the Revised Cardiac Risk Index (RCRI) score. Results. In the derivation cohort, there were 1,452 deaths. The algorithm discriminates mortality with an AUC of 0.83 (95% CI 0.79-0.87) surpassing the discrimination of the RCRI score with an AUC of 0.67 (CI 0.61-0.72) in the held out test cohort. Patients determined to be high risk by the deep learning model's risk prediction had an unadjusted odds ratio (OR) of 8.83 (5.57-13.20) for post-operative mortality as compared to an unadjusted OR of 2.08 (CI 0.77-3.50) for post-operative mortality for RCRI greater than 2. The deep learning algorithm performed similarly for patients undergoing cardiac surgery with an AUC of 0.85 (CI 0.77-0.92), non-cardiac surgery with an AUC of 0.83 (0.79-0.88), and catherization or endoscopy suite procedures with an AUC of 0.76 (0.72-0.81). The algorithm similarly discriminated risk for mortality in two separate external validation cohorts from independent healthcare systems with AUCs of 0.79 (0.75-0.83) and 0.75 (0.74-0.76) respectively. Conclusion. The findings demonstrate how a novel deep learning algorithm, applied to pre-operative ECGs, can improve discrimination of post-operative mortality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.03242v1-abstract-full').style.display = 'none'; document.getElementById('2205.03242v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.11640">arXiv:2204.11640</a> <span> [<a href="https://arxiv.org/pdf/2204.11640">pdf</a>, <a href="https://arxiv.org/format/2204.11640">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TPAMI.2022.3172214">10.1109/TPAMI.2022.3172214 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zheng%2C+Z">Ziyang Zheng</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Wenrui Dai</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+D">Duoduo Xue</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenglin Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junni Zou</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2204.11640v2-abstract-short" style="display: inline;"> It is promising to solve linear inverse problems by unfolding iterative algorithms (e.g., iterative shrinkage thresholding algorithm (ISTA)) as deep neural networks (DNNs) with learnable parameters. However, existing ISTA-based unfolded algorithms restrict the network architectures for iterative updates with the partial weight coupling structure to guarantee convergence. In this paper, we propose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.11640v2-abstract-full').style.display = 'inline'; document.getElementById('2204.11640v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.11640v2-abstract-full" style="display: none;"> It is promising to solve linear inverse problems by unfolding iterative algorithms (e.g., iterative shrinkage thresholding algorithm (ISTA)) as deep neural networks (DNNs) with learnable parameters. However, existing ISTA-based unfolded algorithms restrict the network architectures for iterative updates with the partial weight coupling structure to guarantee convergence. In this paper, we propose hybrid ISTA to unfold ISTA with both pre-computed and learned parameters by incorporating free-form DNNs (i.e., DNNs with arbitrary feasible and reasonable network architectures), while ensuring theoretical convergence. We first develop HCISTA to improve the efficiency and flexibility of classical ISTA (with pre-computed parameters) without compromising the convergence rate in theory. Furthermore, the DNN-based hybrid algorithm is generalized to popular variants of learned ISTA, dubbed HLISTA, to enable a free architecture of learned parameters with a guarantee of linear convergence. To our best knowledge, this paper is the first to provide a convergence-provable framework that enables free-form DNNs in ISTA-based unfolded algorithms. This framework is general to endow arbitrary DNNs for solving linear inverse problems with convergence guarantees. Extensive experiments demonstrate that hybrid ISTA can reduce the reconstruction error with an improved convergence rate in the tasks of sparse recovery and compressive sensing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.11640v2-abstract-full').style.display = 'none'; document.getElementById('2204.11640v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">109 pages, 16 figures; this is a draft and the final version has been accepted by TPAMI (DOI: 10.1109/TPAMI.2022.3172214)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.06230">arXiv:2204.06230</a> <span> [<a href="https://arxiv.org/pdf/2204.06230">pdf</a>, <a href="https://arxiv.org/ps/2204.06230">ps</a>, <a href="https://arxiv.org/format/2204.06230">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Performance Analysis of Wireless Network Aided by Discrete-Phase-Shifter IRS </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Dong%2C+R">Rongen Dong</a>, <a href="/search/eess?searchtype=author&query=Teng%2C+Y">Yin Teng</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Z">Zhongwen Sun</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jun Zou</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+M">Mengxing Huang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jun Li</a>, <a href="/search/eess?searchtype=author&query=Shu%2C+F">Feng Shu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiangzhou Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2204.06230v1-abstract-short" style="display: inline;"> Discrete phase shifters of intelligent reflecting surface (IRS) generates phase quantization error (QE) and degrades the receive performance at the receiver. To make an analysis of the performance loss caused by IRS with phase QE, based on the law of large numbers, the closed-form expressions of signal-to-noise ratio (SNR) performance loss (PL), achievable rate (AR), and bit error rate (BER) are s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.06230v1-abstract-full').style.display = 'inline'; document.getElementById('2204.06230v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.06230v1-abstract-full" style="display: none;"> Discrete phase shifters of intelligent reflecting surface (IRS) generates phase quantization error (QE) and degrades the receive performance at the receiver. To make an analysis of the performance loss caused by IRS with phase QE, based on the law of large numbers, the closed-form expressions of signal-to-noise ratio (SNR) performance loss (PL), achievable rate (AR), and bit error rate (BER) are successively derived under line-of-sight (LoS) channels and Rayleigh channels. Moreover, based on the Taylor series expansion, the approximate simple closed form of PL of IRS with approximate QE is also given. The simulation results show that the performance losses of SNR and AR decrease as the number of quantization bits increase, while they gradually increase with the number of IRS phase shifter elements increase. Regardless of LoS channels or Rayleigh channels, when the number of quantization bits is larger than or equal to 3, the performance losses of SNR and AR are less than 0.23dB and 0.08bits/s/Hz, respectively, and the BER performance degradation is trivial. In particular, the performance loss difference between IRS with QE and IRS with approximate QE is negligible when the number of quantization bits is not less than 2. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.06230v1-abstract-full').style.display = 'none'; document.getElementById('2204.06230v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.08807">arXiv:2203.08807</a> <span> [<a href="https://arxiv.org/pdf/2203.08807">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1126/sciadv.abq6147">10.1126/sciadv.abq6147 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Daneshjou%2C+R">Roxana Daneshjou</a>, <a href="/search/eess?searchtype=author&query=Vodrahalli%2C+K">Kailas Vodrahalli</a>, <a href="/search/eess?searchtype=author&query=Novoa%2C+R+A">Roberto A Novoa</a>, <a href="/search/eess?searchtype=author&query=Jenkins%2C+M">Melissa Jenkins</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+W">Weixin Liang</a>, <a href="/search/eess?searchtype=author&query=Rotemberg%2C+V">Veronica Rotemberg</a>, <a href="/search/eess?searchtype=author&query=Ko%2C+J">Justin Ko</a>, <a href="/search/eess?searchtype=author&query=Swetter%2C+S+M">Susan M Swetter</a>, <a href="/search/eess?searchtype=author&query=Bailey%2C+E+E">Elizabeth E Bailey</a>, <a href="/search/eess?searchtype=author&query=Gevaert%2C+O">Olivier Gevaert</a>, <a href="/search/eess?searchtype=author&query=Mukherjee%2C+P">Pritam Mukherjee</a>, <a href="/search/eess?searchtype=author&query=Phung%2C+M">Michelle Phung</a>, <a href="/search/eess?searchtype=author&query=Yekrang%2C+K">Kiana Yekrang</a>, <a href="/search/eess?searchtype=author&query=Fong%2C+B">Bradley Fong</a>, <a href="/search/eess?searchtype=author&query=Sahasrabudhe%2C+R">Rachna Sahasrabudhe</a>, <a href="/search/eess?searchtype=author&query=Allerup%2C+J+A+C">Johan A. C. Allerup</a>, <a href="/search/eess?searchtype=author&query=Okata-Karigane%2C+U">Utako Okata-Karigane</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a>, <a href="/search/eess?searchtype=author&query=Chiou%2C+A">Albert Chiou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.08807v1-abstract-short" style="display: inline;"> Access to dermatological care is a major issue, with an estimated 3 billion people lacking access to care globally. Artificial intelligence (AI) may aid in triaging skin diseases. However, most AI models have not been rigorously assessed on images of diverse skin tones or uncommon diseases. To ascertain potential biases in algorithm performance in this context, we curated the Diverse Dermatology I… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.08807v1-abstract-full').style.display = 'inline'; document.getElementById('2203.08807v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.08807v1-abstract-full" style="display: none;"> Access to dermatological care is a major issue, with an estimated 3 billion people lacking access to care globally. Artificial intelligence (AI) may aid in triaging skin diseases. However, most AI models have not been rigorously assessed on images of diverse skin tones or uncommon diseases. To ascertain potential biases in algorithm performance in this context, we curated the Diverse Dermatology Images (DDI) dataset-the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones. Using this dataset of 656 images, we show that state-of-the-art dermatology AI models perform substantially worse on DDI, with receiver operator curve area under the curve (ROC-AUC) dropping by 27-36 percent compared to the models' original test results. All the models performed worse on dark skin tones and uncommon diseases, which are represented in the DDI dataset. Additionally, we find that dermatologists, who typically provide visual labels for AI training and test datasets, also perform worse on images of dark skin tones and uncommon diseases compared to ground truth biopsy annotations. Finally, fine-tuning AI models on the well-characterized and diverse DDI images closed the performance gap between light and dark skin tones. Moreover, algorithms fine-tuned on diverse skin tones outperformed dermatologists on identifying malignancy on images of dark skin tones. Our findings identify important weaknesses and biases in dermatology AI that need to be addressed to ensure reliable application to diverse patients and diseases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.08807v1-abstract-full').style.display = 'none'; document.getElementById('2203.08807v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.01494">arXiv:2202.01494</a> <span> [<a href="https://arxiv.org/pdf/2202.01494">pdf</a>, <a href="https://arxiv.org/format/2202.01494">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PARCEL: Physics-based Unsupervised Contrastive Representation Learning for Multi-coil MR Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shanshan Wang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ruoyou Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cheng Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Juan Zou</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Ziyao Zhang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qiegen Liu</a>, <a href="/search/eess?searchtype=author&query=Xi%2C+Y">Yan Xi</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2202.01494v3-abstract-short" style="display: inline;"> With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.01494v3-abstract-full').style.display = 'inline'; document.getElementById('2202.01494v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.01494v3-abstract-full" style="display: none;"> With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics-bAsed unsupeRvised Contrastive rEpresentation Learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has a parallel framework to contrastively learn two branches of model-based unrolling networks from augmented undersampled multi-coil k-space data. A sophisticated co-training loss with three essential components has been designed to guide the two networks in capturing the inherent features and representations for MR images. And the final MR image is reconstructed with the trained contrastive networks. PARCEL was evaluated on two vivo datasets and compared to five state-of-the-art methods. The results show that PARCEL is able to learn essential representations for accurate MR reconstruction without relying on fully sampled datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.01494v3-abstract-full').style.display = 'none'; document.getElementById('2202.01494v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.00097">arXiv:2201.00097</a> <span> [<a href="https://arxiv.org/pdf/2201.00097">pdf</a>, <a href="https://arxiv.org/format/2201.00097">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Adversarial Attack via Dual-Stage Network Erosion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Duan%2C+Y">Yexin Duan</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junhua Zou</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+X">Xingyu Zhou</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wu Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jin Zhang</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+Z">Zhisong Pan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2201.00097v1-abstract-short" style="display: inline;"> Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable adversarial examples under the black-box setting. To this end, this paper proposes to improve the transferability of adversarial examples, and applies dual-stag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.00097v1-abstract-full').style.display = 'inline'; document.getElementById('2201.00097v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.00097v1-abstract-full" style="display: none;"> Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable adversarial examples under the black-box setting. To this end, this paper proposes to improve the transferability of adversarial examples, and applies dual-stage feature-level perturbations to an existing model to implicitly create a set of diverse models. Then these models are fused by the longitudinal ensemble during the iterations. The proposed method is termed Dual-Stage Network Erosion (DSNE). We conduct comprehensive experiments both on non-residual and residual networks, and obtain more transferable adversarial examples with the computational cost similar to the state-of-the-art method. In particular, for the residual networks, the transferability of the adversarial examples can be significantly improved by biasing the residual block information to the skip connections. Our work provides new insights into the architectural vulnerability of neural networks and presents new challenges to the robustness of neural networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.00097v1-abstract-full').style.display = 'none'; document.getElementById('2201.00097v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.08006">arXiv:2111.08006</a> <span> [<a href="https://arxiv.org/pdf/2111.08006">pdf</a>, <a href="https://arxiv.org/format/2111.08006">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1126/sciadv.abq6147">10.1126/sciadv.abq6147 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Disparities in Dermatology AI: Assessments Using Diverse Clinical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Daneshjou%2C+R">Roxana Daneshjou</a>, <a href="/search/eess?searchtype=author&query=Vodrahalli%2C+K">Kailas Vodrahalli</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+W">Weixin Liang</a>, <a href="/search/eess?searchtype=author&query=Novoa%2C+R+A">Roberto A Novoa</a>, <a href="/search/eess?searchtype=author&query=Jenkins%2C+M">Melissa Jenkins</a>, <a href="/search/eess?searchtype=author&query=Rotemberg%2C+V">Veronica Rotemberg</a>, <a href="/search/eess?searchtype=author&query=Ko%2C+J">Justin Ko</a>, <a href="/search/eess?searchtype=author&query=Swetter%2C+S+M">Susan M Swetter</a>, <a href="/search/eess?searchtype=author&query=Bailey%2C+E+E">Elizabeth E Bailey</a>, <a href="/search/eess?searchtype=author&query=Gevaert%2C+O">Olivier Gevaert</a>, <a href="/search/eess?searchtype=author&query=Mukherjee%2C+P">Pritam Mukherjee</a>, <a href="/search/eess?searchtype=author&query=Phung%2C+M">Michelle Phung</a>, <a href="/search/eess?searchtype=author&query=Yekrang%2C+K">Kiana Yekrang</a>, <a href="/search/eess?searchtype=author&query=Fong%2C+B">Bradley Fong</a>, <a href="/search/eess?searchtype=author&query=Sahasrabudhe%2C+R">Rachna Sahasrabudhe</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">James Zou</a>, <a href="/search/eess?searchtype=author&query=Chiou%2C+A">Albert Chiou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.08006v1-abstract-short" style="display: inline;"> More than 3 billion people lack access to care for skin disease. AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases. To address this, we curated the Diverse Dermatology Images (DDI) dataset - the first publicly available, pathologically confirmed images featuring diverse skin tones. We show tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.08006v1-abstract-full').style.display = 'inline'; document.getElementById('2111.08006v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.08006v1-abstract-full" style="display: none;"> More than 3 billion people lack access to care for skin disease. AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases. To address this, we curated the Diverse Dermatology Images (DDI) dataset - the first publicly available, pathologically confirmed images featuring diverse skin tones. We show that state-of-the-art dermatology AI models perform substantially worse on DDI, with ROC-AUC dropping 29-40 percent compared to the models' original results. We find that dark skin tones and uncommon diseases, which are well represented in the DDI dataset, lead to performance drop-offs. Additionally, we show that state-of-the-art robust training methods cannot correct for these biases without diverse training data. Our findings identify important weaknesses and biases in dermatology AI that need to be addressed to ensure reliable application to diverse patients and across all disease. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.08006v1-abstract-full').style.display = 'none'; document.getElementById('2111.08006v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Machine Learning for Health (ML4H) - Extended Abstract</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.12511">arXiv:2106.12511</a> <span> [<a href="https://arxiv.org/pdf/2106.12511">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1001/jamacardio.2021.6059">10.1001/jamacardio.2021.6059 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Duffy%2C+G">Grant Duffy</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+P+P">Paul P Cheng</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+N">Neal Yuan</a>, <a href="/search/eess?searchtype=author&query=He%2C+B">Bryan He</a>, <a href="/search/eess?searchtype=author&query=Kwan%2C+A+C">Alan C. Kwan</a>, <a href="/search/eess?searchtype=author&query=Shun-Shin%2C+M+J">Matthew J. Shun-Shin</a>, <a href="/search/eess?searchtype=author&query=Alexander%2C+K+M">Kevin M. Alexander</a>, <a href="/search/eess?searchtype=author&query=Ebinger%2C+J">Joseph Ebinger</a>, <a href="/search/eess?searchtype=author&query=Lungren%2C+M+P">Matthew P. Lungren</a>, <a href="/search/eess?searchtype=author&query=Rader%2C+F">Florian Rader</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+D+H">David H. Liang</a>, <a href="/search/eess?searchtype=author&query=Schnittger%2C+I">Ingela Schnittger</a>, <a href="/search/eess?searchtype=author&query=Ashley%2C+E+A">Euan A. Ashley</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J+Y">James Y. Zou</a>, <a href="/search/eess?searchtype=author&query=Patel%2C+J">Jignesh Patel</a>, <a href="/search/eess?searchtype=author&query=Witteles%2C+R">Ronald Witteles</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+S">Susan Cheng</a>, <a href="/search/eess?searchtype=author&query=Ouyang%2C+D">David Ouyang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.12511v1-abstract-short" style="display: inline;"> Left ventricular hypertrophy (LVH) results from chronic remodeling caused by a broad range of systemic and cardiovascular disease including hypertension, aortic stenosis, hypertrophic cardiomyopathy, and cardiac amyloidosis. Early detection and characterization of LVH can significantly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.12511v1-abstract-full').style.display = 'inline'; document.getElementById('2106.12511v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.12511v1-abstract-full" style="display: none;"> Left ventricular hypertrophy (LVH) results from chronic remodeling caused by a broad range of systemic and cardiovascular disease including hypertension, aortic stenosis, hypertrophic cardiomyopathy, and cardiac amyloidosis. Early detection and characterization of LVH can significantly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating etiologies of LVH. To overcome this challenge, we present EchoNet-LVH - a deep learning workflow that automatically quantifies ventricular hypertrophy with precision equal to human experts and predicts etiology of LVH. Trained on 28,201 echocardiogram videos, our model accurately measures intraventricular wall thickness (mean absolute error [MAE] 1.4mm, 95% CI 1.2-1.5mm), left ventricular diameter (MAE 2.4mm, 95% CI 2.2-2.6mm), and posterior wall thickness (MAE 1.2mm, 95% CI 1.1-1.3mm) and classifies cardiac amyloidosis (area under the curve of 0.83) and hypertrophic cardiomyopathy (AUC 0.98) from other etiologies of LVH. In external datasets from independent domestic and international healthcare systems, EchoNet-LVH accurately quantified ventricular parameters (R2 of 0.96 and 0.90 respectively) and detected cardiac amyloidosis (AUC 0.79) and hypertrophic cardiomyopathy (AUC 0.89) on the domestic external validation site. Leveraging measurements across multiple heart beats, our model can more accurately identify subtle changes in LV geometry and its causal etiologies. Compared to human experts, EchoNet-LVH is fully automated, allowing for reproducible, precise measurements, and lays the foundation for precision diagnosis of cardiac hypertrophy. As a resource to promote further innovation, we also make publicly available a large dataset of 23,212 annotated echocardiogram videos. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.12511v1-abstract-full').style.display = 'none'; document.getElementById('2106.12511v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.09910">arXiv:2106.09910</a> <span> [<a href="https://arxiv.org/pdf/2106.09910">pdf</a>, <a href="https://arxiv.org/format/2106.09910">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Message Passing in Graph Convolution Networks via Adaptive Filter Banks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+X">Xing Gao</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Wenrui Dai</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenglin Li</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Junni Zou</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</a>, <a href="/search/eess?searchtype=author&query=Frossard%2C+P">Pascal Frossard</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.09910v1-abstract-short" style="display: inline;"> Graph convolution networks, like message passing graph convolution networks (MPGCNs), have been a powerful tool in representation learning of networked data. However, when data is heterogeneous, most architectures are limited as they employ a single strategy to handle multi-channel graph signals and they typically focus on low-frequency information. In this paper, we present a novel graph convolut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.09910v1-abstract-full').style.display = 'inline'; document.getElementById('2106.09910v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.09910v1-abstract-full" style="display: none;"> Graph convolution networks, like message passing graph convolution networks (MPGCNs), have been a powerful tool in representation learning of networked data. However, when data is heterogeneous, most architectures are limited as they employ a single strategy to handle multi-channel graph signals and they typically focus on low-frequency information. In this paper, we present a novel graph convolution operator, termed BankGCN, which keeps benefits of message passing models, but extends their capabilities beyond `low-pass' features. It decomposes multi-channel signals on graphs into subspaces and handles particular information in each subspace with an adapted filter. The filters of all subspaces have different frequency responses and together form a filter bank. Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank. Importantly, the filter bank and the signal decomposition are jointly learned to adapt to the spectral characteristics of data and to target applications. Furthermore, this is implemented almost without extra parameters in comparison with most existing MPGCNs. Experimental results show that the proposed convolution operator permits to achieve excellent performance in graph classification on a collection of benchmark graph datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.09910v1-abstract-full').style.display = 'none'; document.getElementById('2106.09910v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.06634">arXiv:2105.06634</a> <span> [<a href="https://arxiv.org/pdf/2105.06634">pdf</a>, <a href="https://arxiv.org/ps/2105.06634">ps</a>, <a href="https://arxiv.org/format/2105.06634">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Fast Ambiguous DOA Elimination Method of DOA Measurement for Hybrid Massive MIMO Receiver </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+N">Nuo Chen</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+X">Xinyi Jiang</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+B">Baihua Shi</a>, <a href="/search/eess?searchtype=author&query=Teng%2C+Y">Yin Teng</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jinhui Lu</a>, <a href="/search/eess?searchtype=author&query=Shu%2C+F">Feng Shu</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jun Zou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jun Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiangzhou Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2105.06634v1-abstract-short" style="display: inline;"> DOA estimation for massive multiple-input multiple-output (MIMO) system can provide ultra-high-resolution angle estimation. However, due to the high computational complexity and cost of all digital MIMO systems, a hybrid analog digital (HAD) structure MIMO was proposed. In this paper, a fast ambiguous phase elimination method is proposed to solve the problem of direction-finding ambiguity caused b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.06634v1-abstract-full').style.display = 'inline'; document.getElementById('2105.06634v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.06634v1-abstract-full" style="display: none;"> DOA estimation for massive multiple-input multiple-output (MIMO) system can provide ultra-high-resolution angle estimation. However, due to the high computational complexity and cost of all digital MIMO systems, a hybrid analog digital (HAD) structure MIMO was proposed. In this paper, a fast ambiguous phase elimination method is proposed to solve the problem of direction-finding ambiguity caused by the HAD MIMO. Only two-data-blocks are used to realize DOA estimation. Simulation results show that the proposed method can greatly reduce the estimation delay with a slight performance loss. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.06634v1-abstract-full').style.display = 'none'; document.getElementById('2105.06634v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.10325">arXiv:2011.10325</a> <span> [<a href="https://arxiv.org/pdf/2011.10325">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1049/cp.2019.0901">10.1049/cp.2019.0901 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Improvement of accuracy for measurement of 100-km fibre latency with Correlation OTDR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Azendorf%2C+F">Florian Azendorf</a>, <a href="/search/eess?searchtype=author&query=Dochhan%2C+A">Annika Dochhan</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jim Zou</a>, <a href="/search/eess?searchtype=author&query=Schmauss%2C+B">Bernhard Schmauss</a>, <a href="/search/eess?searchtype=author&query=Eiselt%2C+M">Michael Eiselt</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2011.10325v1-abstract-short" style="display: inline;"> We measured the latency of a 100 km fibre link using a Correlation OTDR. Improvements over previous results were achieved by increasing the probe signal rate to 10 Gbit/s, using dispersion compensation gratings, and coupling the receiver time base to an external PPS signal. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.10325v1-abstract-full" style="display: none;"> We measured the latency of a 100 km fibre link using a Correlation OTDR. Improvements over previous results were achieved by increasing the probe signal rate to 10 Gbit/s, using dispersion compensation gratings, and coupling the receiver time base to an external PPS signal. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.10325v1-abstract-full').style.display = 'none'; document.getElementById('2011.10325v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 762055 (BlueSpace Project)</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> European Conference on Optical Communication (ECOC) 2019 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.04988">arXiv:2011.04988</a> <span> [<a href="https://arxiv.org/pdf/2011.04988">pdf</a>, <a href="https://arxiv.org/format/2011.04988">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> AIM 2020 Challenge on Rendering Realistic Bokeh </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ignatov%2C+A">Andrey Ignatov</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Qian%2C+M">Ming Qian</a>, <a href="/search/eess?searchtype=author&query=Qiao%2C+C">Congyu Qiao</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+J">Jiamin Lin</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Z">Zhenyu Guo</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenghua Li</a>, <a href="/search/eess?searchtype=author&query=Leng%2C+C">Cong Leng</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+J">Jian Cheng</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+J">Juewen Peng</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+X">Xianrui Luo</a>, <a href="/search/eess?searchtype=author&query=Xian%2C+K">Ke Xian</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Z">Zijin Wu</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+Z">Zhiguo Cao</a>, <a href="/search/eess?searchtype=author&query=Puthussery%2C+D">Densen Puthussery</a>, <a href="/search/eess?searchtype=author&query=C%2C+J">Jiji C V</a>, <a href="/search/eess?searchtype=author&query=S%2C+H+P">Hrishikesh P S</a>, <a href="/search/eess?searchtype=author&query=Kuriakose%2C+M">Melvin Kuriakose</a>, <a href="/search/eess?searchtype=author&query=Dutta%2C+S">Saikat Dutta</a>, <a href="/search/eess?searchtype=author&query=Das%2C+S+D">Sourya Dipta Das</a>, <a href="/search/eess?searchtype=author&query=Shah%2C+N+A">Nisarg A. Shah</a>, <a href="/search/eess?searchtype=author&query=Purohit%2C+K">Kuldeep Purohit</a>, <a href="/search/eess?searchtype=author&query=Kandula%2C+P">Praveen Kandula</a>, <a href="/search/eess?searchtype=author&query=Suin%2C+M">Maitreya Suin</a>, <a href="/search/eess?searchtype=author&query=Rajagopalan%2C+A+N">A. N. Rajagopalan</a> , et al. (10 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2011.04988v1-abstract-short" style="display: inline;"> This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04988v1-abstract-full').style.display = 'inline'; document.getElementById('2011.04988v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.04988v1-abstract-full" style="display: none;"> This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The participants had to render bokeh effect based on only one single frame without any additional data from other cameras or sensors. The target metric used in this challenge combined the runtime and the perceptual quality of the solutions measured in the user study. To ensure the efficiency of the submitted models, we measured their runtime on standard desktop CPUs as well as were running the models on smartphone GPUs. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical bokeh effect rendering problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04988v1-abstract-full').style.display = 'none'; document.getElementById('2011.04988v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in ECCV 2020 Workshop (Advances in Image Manipulation), https://data.vision.ee.ethz.ch/cvl/aim20/</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zou%2C+J&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zou%2C+J&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zou%2C+J&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository