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 1–24 of 24 results for author: <span class="mathjax">Black, S</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/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Black%2C+S">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="Black, S"> </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=Black%2C+S&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="Black, S"> <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> <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/2409.03012">arXiv:2409.03012</a> <span> [<a href="https://arxiv.org/pdf/2409.03012">pdf</a>, <a href="https://arxiv.org/format/2409.03012">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="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Design and Evaluation of Camera-Centric Mobile Crowdsourcing Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stylianou%2C+A">Abby Stylianou</a>, <a href="/search/cs?searchtype=author&query=Brachman%2C+M">Michelle Brachman</a>, <a href="/search/cs?searchtype=author&query=Wazzan%2C+A">Albatool Wazzan</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Samuel Black</a>, <a href="/search/cs?searchtype=author&query=Souvenir%2C+R">Richard Souvenir</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="2409.03012v1-abstract-short" style="display: inline;"> The data that underlies automated methods in computer vision and machine learning, such as image retrieval and fine-grained recognition, often comes from crowdsourcing. In contexts that rely on the intrinsic motivation of users, we seek to understand how the application design affects a user's willingness to contribute and the quantity and quality of the data they capture. In this project, we desi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03012v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03012v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03012v1-abstract-full" style="display: none;"> The data that underlies automated methods in computer vision and machine learning, such as image retrieval and fine-grained recognition, often comes from crowdsourcing. In contexts that rely on the intrinsic motivation of users, we seek to understand how the application design affects a user's willingness to contribute and the quantity and quality of the data they capture. In this project, we designed three versions of a camera-based mobile crowdsourcing application, which varied in the amount of labeling effort requested of the user and conducted a user study to evaluate the trade-off between the level of user-contributed information requested and the quantity and quality of labeled images collected. The results suggest that higher levels of user labeling do not lead to reduced contribution. Users collected and annotated the most images using the application version with the highest requested level of labeling with no decrease in user satisfaction. In preliminary experiments, the additional labeled data supported increased performance on an image retrieval task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03012v1-abstract-full').style.display = 'none'; document.getElementById('2409.03012v1-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 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/2408.13333">arXiv:2408.13333</a> <span> [<a href="https://arxiv.org/pdf/2408.13333">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Mastering the Digital Art of War: Developing Intelligent Combat Simulation Agents for Wargaming Using Hierarchical Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Scotty Black</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="2408.13333v1-abstract-short" style="display: inline;"> In today's rapidly evolving military landscape, advancing artificial intelligence (AI) in support of wargaming becomes essential. Despite reinforcement learning (RL) showing promise for developing intelligent agents, conventional RL faces limitations in handling the complexity inherent in combat simulations. This dissertation proposes a comprehensive approach, including targeted observation abstra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13333v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13333v1-abstract-full" style="display: none;"> In today's rapidly evolving military landscape, advancing artificial intelligence (AI) in support of wargaming becomes essential. Despite reinforcement learning (RL) showing promise for developing intelligent agents, conventional RL faces limitations in handling the complexity inherent in combat simulations. This dissertation proposes a comprehensive approach, including targeted observation abstractions, multi-model integration, a hybrid AI framework, and an overarching hierarchical reinforcement learning (HRL) framework. Our localized observation abstraction using piecewise linear spatial decay simplifies the RL problem, enhancing computational efficiency and demonstrating superior efficacy over traditional global observation methods. Our multi-model framework combines various AI methodologies, optimizing performance while still enabling the use of diverse, specialized individual behavior models. Our hybrid AI framework synergizes RL with scripted agents, leveraging RL for high-level decisions and scripted agents for lower-level tasks, enhancing adaptability, reliability, and performance. Our HRL architecture and training framework decomposes complex problems into manageable subproblems, aligning with military decision-making structures. Although initial tests did not show improved performance, insights were gained to improve future iterations. This study underscores AI's potential to revolutionize wargaming, emphasizing the need for continued research in this domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13333v1-abstract-full').style.display = 'none'; document.getElementById('2408.13333v1-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 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/2408.13328">arXiv:2408.13328</a> <span> [<a href="https://arxiv.org/pdf/2408.13328">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Localized Observation Abstraction Using Piecewise Linear Spatial Decay for Reinforcement Learning in Combat Simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Scotty Black</a>, <a href="/search/cs?searchtype=author&query=Darken%2C+C">Christian Darken</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="2408.13328v1-abstract-short" style="display: inline;"> In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of the scenarios and available information increases, the training time required to achieve a certain threshold of performance does not just increase, but often do… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13328v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13328v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13328v1-abstract-full" style="display: none;"> In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of the scenarios and available information increases, the training time required to achieve a certain threshold of performance does not just increase, but often does so exponentially. This relationship underscores the profound impact of complexity in training RL agents. This paper introduces a novel approach that addresses this limitation in training artificial intelligence (AI) agents using RL. Traditional RL methods have been shown to struggle in these high-dimensional, dynamic environments due to real-world computational constraints and the known sample inefficiency challenges of RL. To overcome these limitations, we propose a method of localized observation abstraction using piecewise linear spatial decay. This technique simplifies the state space, reducing computational demands while still preserving essential information, thereby enhancing AI training efficiency in dynamic environments where spatial relationships are often critical. Our analysis reveals that this localized observation approach consistently outperforms the more traditional global observation approach across increasing scenario complexity levels. This paper advances the research on observation abstractions for RL, illustrating how localized observation with piecewise linear spatial decay can provide an effective solution to large state representation challenges in dynamic environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13328v1-abstract-full').style.display = 'none'; document.getElementById('2408.13328v1-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 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/2405.14782">arXiv:2405.14782</a> <span> [<a href="https://arxiv.org/pdf/2405.14782">pdf</a>, <a href="https://arxiv.org/format/2405.14782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Lessons from the Trenches on Reproducible Evaluation of Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Biderman%2C+S">Stella Biderman</a>, <a href="/search/cs?searchtype=author&query=Schoelkopf%2C+H">Hailey Schoelkopf</a>, <a href="/search/cs?searchtype=author&query=Sutawika%2C+L">Lintang Sutawika</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Leo Gao</a>, <a href="/search/cs?searchtype=author&query=Tow%2C+J">Jonathan Tow</a>, <a href="/search/cs?searchtype=author&query=Abbasi%2C+B">Baber Abbasi</a>, <a href="/search/cs?searchtype=author&query=Aji%2C+A+F">Alham Fikri Aji</a>, <a href="/search/cs?searchtype=author&query=Ammanamanchi%2C+P+S">Pawan Sasanka Ammanamanchi</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sidney Black</a>, <a href="/search/cs?searchtype=author&query=Clive%2C+J">Jordan Clive</a>, <a href="/search/cs?searchtype=author&query=DiPofi%2C+A">Anthony DiPofi</a>, <a href="/search/cs?searchtype=author&query=Etxaniz%2C+J">Julen Etxaniz</a>, <a href="/search/cs?searchtype=author&query=Fattori%2C+B">Benjamin Fattori</a>, <a href="/search/cs?searchtype=author&query=Forde%2C+J+Z">Jessica Zosa Forde</a>, <a href="/search/cs?searchtype=author&query=Foster%2C+C">Charles Foster</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+J">Jeffrey Hsu</a>, <a href="/search/cs?searchtype=author&query=Jaiswal%2C+M">Mimansa Jaiswal</a>, <a href="/search/cs?searchtype=author&query=Lee%2C+W+Y">Wilson Y. Lee</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haonan Li</a>, <a href="/search/cs?searchtype=author&query=Lovering%2C+C">Charles Lovering</a>, <a href="/search/cs?searchtype=author&query=Muennighoff%2C+N">Niklas Muennighoff</a>, <a href="/search/cs?searchtype=author&query=Pavlick%2C+E">Ellie Pavlick</a>, <a href="/search/cs?searchtype=author&query=Phang%2C+J">Jason Phang</a>, <a href="/search/cs?searchtype=author&query=Skowron%2C+A">Aviya Skowron</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+S">Samson Tan</a> , et al. (5 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="2405.14782v2-abstract-short" style="display: inline;"> Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14782v2-abstract-full').style.display = 'inline'; document.getElementById('2405.14782v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.14782v2-abstract-full" style="display: none;"> Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers. First, we provide an overview of common challenges faced in language model evaluation. Second, we delineate best practices for addressing or lessening the impact of these challenges on research. Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues. We describe the features of the library as well as case studies in which the library has been used to alleviate these methodological concerns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.14782v2-abstract-full').style.display = 'none'; document.getElementById('2405.14782v2-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">v1</span> submitted 23 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/2402.17891">arXiv:2402.17891</a> <span> [<a href="https://arxiv.org/pdf/2402.17891">pdf</a>, <a href="https://arxiv.org/format/2402.17891">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> </div> </div> <p class="title is-5 mathjax"> Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xinyu Yang</a>, <a href="/search/cs?searchtype=author&query=Rahmani%2C+H">Hossein Rahmani</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sue Black</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+M">Bryan M. Williams</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="2402.17891v2-abstract-short" style="display: inline;"> Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement, introducing additional stages or proposing offline modules. This can cause optimization difficulties for single-stage methods and limit generalizability. In this study… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17891v2-abstract-full').style.display = 'inline'; document.getElementById('2402.17891v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.17891v2-abstract-full" style="display: none;"> Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement, introducing additional stages or proposing offline modules. This can cause optimization difficulties for single-stage methods and limit generalizability. In this study, we aim to reduce the observed CAM inconsistency and error to mitigate reliance on refinement processes. We propose an end-to-end WSSS model incorporating guided CAMs, wherein our segmentation model is trained while concurrently optimizing CAMs online. Our method, Co-training with Swapping Assignments (CoSA), leverages a dual-stream framework, where one sub-network learns from the swapped assignments generated by the other. We introduce three techniques: i) soft perplexity-based regularization to penalize uncertain regions; ii) a threshold-searching approach to dynamically revise the confidence threshold; and iii) contrastive separation to address the coexistence problem. CoSA demonstrates exceptional performance, achieving mIoU of 76.2\% and 51.0\% on VOC and COCO validation datasets, respectively, surpassing existing baselines by a substantial margin. Notably, CoSA is the first single-stage approach to outperform all existing multi-stage methods including those with additional supervision. Code is avilable at \url{https://github.com/youshyee/CoSA}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.17891v2-abstract-full').style.display = 'none'; document.getElementById('2402.17891v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 at ECCV24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.06694">arXiv:2402.06694</a> <span> [<a href="https://arxiv.org/pdf/2402.06694">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Scaling Intelligent Agents in Combat Simulations for Wargaming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Scotty Black</a>, <a href="/search/cs?searchtype=author&query=Darken%2C+C">Christian Darken</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="2402.06694v1-abstract-short" style="display: inline;"> Remaining competitive in future conflicts with technologically-advanced competitors requires us to accelerate our research and development in artificial intelligence (AI) for wargaming. More importantly, leveraging machine learning for intelligent combat behavior development will be key to one day achieving superhuman performance in this domain--elevating the quality and accelerating the speed of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06694v1-abstract-full').style.display = 'inline'; document.getElementById('2402.06694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.06694v1-abstract-full" style="display: none;"> Remaining competitive in future conflicts with technologically-advanced competitors requires us to accelerate our research and development in artificial intelligence (AI) for wargaming. More importantly, leveraging machine learning for intelligent combat behavior development will be key to one day achieving superhuman performance in this domain--elevating the quality and accelerating the speed of our decisions in future wars. Although deep reinforcement learning (RL) continues to show promising results in intelligent agent behavior development in games, it has yet to perform at or above the human level in the long-horizon, complex tasks typically found in combat modeling and simulation. Capitalizing on the proven potential of RL and recent successes of hierarchical reinforcement learning (HRL), our research is investigating and extending the use of HRL to create intelligent agents capable of performing effectively in these large and complex simulation environments. Our ultimate goal is to develop an agent capable of superhuman performance that could then serve as an AI advisor to military planners and decision-makers. This papers covers our ongoing approach and the first three of our five research areas aimed at managing the exponential growth of computations that have thus far limited the use of AI in combat simulations: (1) developing an HRL training framework and agent architecture for combat units; (2) developing a multi-model framework for agent decision-making; (3) developing dimension-invariant observation abstractions of the state space to manage the exponential growth of computations; (4) developing an intrinsic rewards engine to enable long-term planning; and (5) implementing this framework into a higher-fidelity combat simulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06694v1-abstract-full').style.display = 'none'; document.getElementById('2402.06694v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">arXiv admin note: text overlap with arXiv:2402.06075</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> I/ITSEC Conference Proceedings 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.06075">arXiv:2402.06075</a> <span> [<a href="https://arxiv.org/pdf/2402.06075">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="Artificial Intelligence">cs.AI</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/10.14339/STO-MP-MSG-207-23-PDF">10.14339/STO-MP-MSG-207-23-PDF <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Scaling Artificial Intelligence for Digital Wargaming in Support of Decision-Making </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Scotty Black</a>, <a href="/search/cs?searchtype=author&query=Darken%2C+C">Christian Darken</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="2402.06075v1-abstract-short" style="display: inline;"> In this unprecedented era of technology-driven transformation, it becomes more critical than ever that we aggressively invest in developing robust artificial intelligence (AI) for wargaming in support of decision-making. By advancing AI-enabled systems and pairing these with human judgment, we will be able to enhance all-domain awareness, improve the speed and quality of our decision cycles, offer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06075v1-abstract-full').style.display = 'inline'; document.getElementById('2402.06075v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.06075v1-abstract-full" style="display: none;"> In this unprecedented era of technology-driven transformation, it becomes more critical than ever that we aggressively invest in developing robust artificial intelligence (AI) for wargaming in support of decision-making. By advancing AI-enabled systems and pairing these with human judgment, we will be able to enhance all-domain awareness, improve the speed and quality of our decision cycles, offer recommendations for novel courses of action, and more rapidly counter our adversary's actions. It therefore becomes imperative that we accelerate the development of AI to help us better address the complexity of modern challenges and dilemmas that currently requires human intelligence and, if possible, attempt to surpass human intelligence--not to replace humans, but to augment and better inform human decision-making at machine speed. Although deep reinforcement learning continues to show promising results in intelligent agent behavior development for the long-horizon, complex tasks typically found in combat modeling and simulation, further research is needed to enable the scaling of AI to deal with these intricate and expansive state-spaces characteristic of wargaming for either concept development, education, or analysis. To help address this challenge, in our research, we are developing and implementing a hierarchical reinforcement learning framework that includes a multi-model approach and dimension-invariant observation abstractions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.06075v1-abstract-full').style.display = 'none'; document.getElementById('2402.06075v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> STO-MP-MSG-207-23 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> NATO STO-MP-MSG-207 2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.13770">arXiv:2312.13770</a> <span> [<a href="https://arxiv.org/pdf/2312.13770">pdf</a>, <a href="https://arxiv.org/format/2312.13770">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> </div> </div> <p class="title is-5 mathjax"> 3D Points Splatting for Real-Time Dynamic Hand Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zheheng Jiang</a>, <a href="/search/cs?searchtype=author&query=Rahmani%2C+H">Hossein Rahmani</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sue Black</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+M">Bryan M. Williams</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="2312.13770v1-abstract-short" style="display: inline;"> We present 3D Points Splatting Hand Reconstruction (3D-PSHR), a real-time and photo-realistic hand reconstruction approach. We propose a self-adaptive canonical points upsampling strategy to achieve high-resolution hand geometry representation. This is followed by a self-adaptive deformation that deforms the hand from the canonical space to the target pose, adapting to the dynamic changing of cano… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13770v1-abstract-full').style.display = 'inline'; document.getElementById('2312.13770v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.13770v1-abstract-full" style="display: none;"> We present 3D Points Splatting Hand Reconstruction (3D-PSHR), a real-time and photo-realistic hand reconstruction approach. We propose a self-adaptive canonical points upsampling strategy to achieve high-resolution hand geometry representation. This is followed by a self-adaptive deformation that deforms the hand from the canonical space to the target pose, adapting to the dynamic changing of canonical points which, in contrast to the common practice of subdividing the MANO model, offers greater flexibility and results in improved geometry fitting. To model texture, we disentangle the appearance color into the intrinsic albedo and pose-aware shading, which are learned through a Context-Attention module. Moreover, our approach allows the geometric and the appearance models to be trained simultaneously in an end-to-end manner. We demonstrate that our method is capable of producing animatable, photorealistic and relightable hand reconstructions using multiple datasets, including monocular videos captured with handheld smartphones and large-scale multi-view videos featuring various hand poses. We also demonstrate that our approach achieves real-time rendering speeds while simultaneously maintaining superior performance compared to existing state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13770v1-abstract-full').style.display = 'none'; document.getElementById('2312.13770v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.08456">arXiv:2307.08456</a> <span> [<a href="https://arxiv.org/pdf/2307.08456">pdf</a>, <a href="https://arxiv.org/format/2307.08456">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"> Domain Adaptation using Silver Standard Masks for Lateral Ventricle Segmentation in FLAIR MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Crystal%2C+O">Owen Crystal</a>, <a href="/search/cs?searchtype=author&query=Maralani%2C+P+J">Pejman J. Maralani</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sandra Black</a>, <a href="/search/cs?searchtype=author&query=Moody%2C+A+R">Alan R. Moody</a>, <a href="/search/cs?searchtype=author&query=Khademi%2C+A">April Khademi</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="2307.08456v1-abstract-short" style="display: inline;"> Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.08456v1-abstract-full').style.display = 'inline'; document.getElementById('2307.08456v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.08456v1-abstract-full" style="display: none;"> Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks were generated from the target domain using a novel conventional image processing ventricular segmentation algorithm and used to supplement the gold standard (GS) data from the source domain, Canadian Atherosclerosis Imaging Network (CAIN). Four models were tested on held-out test sets from four datasets: 1) SS+GS: trained on target SS masks and fine-tuned on source GS masks, 2) GS+SS: trained on source GS masks and fine-tuned on target SS masks, 3) trained on source GS (GS CAIN Only) and 4) trained on target SS masks (SS Only). The SS+GS model had the best and most consistent performance (mean DSC = 0.89, CoV = 0.05) and showed significantly (p < 0.05) higher DSC compared to the GS-only model on three target domains. Results suggest pre-training with noisy labels from the target domain allows the model to adapt to the dataset-specific characteristics and provides robust parameter initialization while fine-tuning with GS masks allows the model to learn detailed features. This method has wide application to other medical imaging problems where labeled data is scarce, and can be used as a per-dataset calibration method to accelerate wide-scale adoption. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.08456v1-abstract-full').style.display = 'none'; document.getElementById('2307.08456v1-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 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">16 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/2307.05745">arXiv:2307.05745</a> <span> [<a href="https://arxiv.org/pdf/2307.05745">pdf</a>, <a href="https://arxiv.org/format/2307.05745">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> CloudSec: An Extensible Automated Reasoning Framework for Cloud Security Policies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Stubbs%2C+J">Joe Stubbs</a>, <a href="/search/cs?searchtype=author&query=Padhy%2C+S">Smruti Padhy</a>, <a href="/search/cs?searchtype=author&query=Cardone%2C+R">Richard Cardone</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Steven Black</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="2307.05745v1-abstract-short" style="display: inline;"> Users increasingly create, manage and share digital resources, including sensitive data, via cloud platforms and APIs. Platforms encode the rules governing access to these resources, referred to as \textit{security policies}, using different systems and semantics. As the number of resources and rules grows, the challenge of reasoning about them collectively increases. Formal methods tools, such as… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.05745v1-abstract-full').style.display = 'inline'; document.getElementById('2307.05745v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.05745v1-abstract-full" style="display: none;"> Users increasingly create, manage and share digital resources, including sensitive data, via cloud platforms and APIs. Platforms encode the rules governing access to these resources, referred to as \textit{security policies}, using different systems and semantics. As the number of resources and rules grows, the challenge of reasoning about them collectively increases. Formal methods tools, such as Satisfiability Modulo Theories (SMT) libraries, can be used to automate the analysis of security policies, but several challenges, including the highly specialized, technical nature of the libraries as well as their variable performance, prevent their broad adoption in cloud systems. In this paper, we present CloudSec, an extensible framework for reasoning about cloud security policies using SMT. CloudSec provides a high-level API that can be used to encode different types of cloud security policies without knowledge of SMT. Further, it is trivial for applications written with CloudSec to utilize and switch between different SMT libraries such as Z3 and CVC5. We demonstrate the use of CloudSec to analyze security policies in Tapis, a cloud-based API for distributed computational research used by tens of thousands of researchers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.05745v1-abstract-full').style.display = 'none'; document.getElementById('2307.05745v1-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, 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/2304.14299">arXiv:2304.14299</a> <span> [<a href="https://arxiv.org/pdf/2304.14299">pdf</a>, <a href="https://arxiv.org/format/2304.14299">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> </div> </div> <p class="title is-5 mathjax"> A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zheheng Jiang</a>, <a href="/search/cs?searchtype=author&query=Rahmani%2C+H">Hossein Rahmani</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sue Black</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B+M">Bryan M. Williams</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="2304.14299v1-abstract-short" style="display: inline;"> Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.14299v1-abstract-full').style.display = 'inline'; document.getElementById('2304.14299v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.14299v1-abstract-full" style="display: none;"> Recently, deep learning based approaches have shown promising results in 3D hand reconstruction from a single RGB image. These approaches can be roughly divided into model-based approaches, which are heavily dependent on the model's parameter space, and model-free approaches, which require large numbers of 3D ground truths to reduce depth ambiguity and struggle in weakly-supervised scenarios. To overcome these issues, we propose a novel probabilistic model to achieve the robustness of model-based approaches and reduced dependence on the model's parameter space of model-free approaches. The proposed probabilistic model incorporates a model-based network as a prior-net to estimate the prior probability distribution of joints and vertices. An Attention-based Mesh Vertices Uncertainty Regression (AMVUR) model is proposed to capture dependencies among vertices and the correlation between joints and mesh vertices to improve their feature representation. We further propose a learning based occlusion-aware Hand Texture Regression model to achieve high-fidelity texture reconstruction. We demonstrate the flexibility of the proposed probabilistic model to be trained in both supervised and weakly-supervised scenarios. The experimental results demonstrate our probabilistic model's state-of-the-art accuracy in 3D hand and texture reconstruction from a single image in both training schemes, including in the presence of severe occlusions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.14299v1-abstract-full').style.display = 'none'; document.getElementById('2304.14299v1-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.08557">arXiv:2304.08557</a> <span> [<a href="https://arxiv.org/pdf/2304.08557">pdf</a>, <a href="https://arxiv.org/format/2304.08557">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> </div> <p class="title is-5 mathjax"> A Decentralized Authorization and Security Framework for Distributed Research Workflows </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cardone%2C+R">Richard Cardone</a>, <a href="/search/cs?searchtype=author&query=Padhy%2C+S">Smruti Padhy</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Steven Black</a>, <a href="/search/cs?searchtype=author&query=Cleveland%2C+S">Sean Cleveland</a>, <a href="/search/cs?searchtype=author&query=Stubbs%2C+J">Joe Stubbs</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="2304.08557v2-abstract-short" style="display: inline;"> Research challenges such as climate change and the search for habitable planets increasingly use academic and commercial computing resources distributed across different institutions and physical sites. Furthermore, such analyses often require a level of automation that precludes direct human interaction, and securing these workflows involves adherence to security policies across institutions. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.08557v2-abstract-full').style.display = 'inline'; document.getElementById('2304.08557v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.08557v2-abstract-full" style="display: none;"> Research challenges such as climate change and the search for habitable planets increasingly use academic and commercial computing resources distributed across different institutions and physical sites. Furthermore, such analyses often require a level of automation that precludes direct human interaction, and securing these workflows involves adherence to security policies across institutions. In this paper, we present a decentralized authorization and security framework that enables researchers to utilize resources across different sites while allowing service providers to maintain autonomy over their secrets and authorization policies. We describe this framework as part of the Tapis platform, a web-based, hosted API used by researchers from multiple institutions, and we measure the performance of various authorization and security queries, including cross-site queries. We conclude with two use case studies -- a project at the University of Hawaii to study climate change and the NASA NEID telescope project that searches the galaxy for exoplanets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.08557v2-abstract-full').style.display = 'none'; document.getElementById('2304.08557v2-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 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. Short version of this paper to be published on COMPSAC 2023 proceedings</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> H.4.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.12312">arXiv:2211.12312</a> <span> [<a href="https://arxiv.org/pdf/2211.12312">pdf</a>, <a href="https://arxiv.org/format/2211.12312">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> </div> </div> <p class="title is-5 mathjax"> Interpreting Neural Networks through the Polytope Lens </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Sid Black</a>, <a href="/search/cs?searchtype=author&query=Sharkey%2C+L">Lee Sharkey</a>, <a href="/search/cs?searchtype=author&query=Grinsztajn%2C+L">Leo Grinsztajn</a>, <a href="/search/cs?searchtype=author&query=Winsor%2C+E">Eric Winsor</a>, <a href="/search/cs?searchtype=author&query=Braun%2C+D">Dan Braun</a>, <a href="/search/cs?searchtype=author&query=Merizian%2C+J">Jacob Merizian</a>, <a href="/search/cs?searchtype=author&query=Parker%2C+K">Kip Parker</a>, <a href="/search/cs?searchtype=author&query=Guevara%2C+C+R">Carlos Ram贸n Guevara</a>, <a href="/search/cs?searchtype=author&query=Millidge%2C+B">Beren Millidge</a>, <a href="/search/cs?searchtype=author&query=Alfour%2C+G">Gabriel Alfour</a>, <a href="/search/cs?searchtype=author&query=Leahy%2C+C">Connor Leahy</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="2211.12312v1-abstract-short" style="display: inline;"> Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons or their linear combinations to understand the representations a network has learned. But there are clues that neurons and their linear combinations are not the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.12312v1-abstract-full').style.display = 'inline'; document.getElementById('2211.12312v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.12312v1-abstract-full" style="display: none;"> Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons or their linear combinations to understand the representations a network has learned. But there are clues that neurons and their linear combinations are not the correct fundamental units of description: directions cannot describe how neural networks use nonlinearities to structure their representations. Moreover, many instances of individual neurons and their combinations are polysemantic (i.e. they have multiple unrelated meanings). Polysemanticity makes interpreting the network in terms of neurons or directions challenging since we can no longer assign a specific feature to a neural unit. In order to find a basic unit of description that does not suffer from these problems, we zoom in beyond just directions to study the way that piecewise linear activation functions (such as ReLU) partition the activation space into numerous discrete polytopes. We call this perspective the polytope lens. The polytope lens makes concrete predictions about the behavior of neural networks, which we evaluate through experiments on both convolutional image classifiers and language models. Specifically, we show that polytopes can be used to identify monosemantic regions of activation space (while directions are not in general monosemantic) and that the density of polytope boundaries reflect semantic boundaries. We also outline a vision for what mechanistic interpretability might look like through the polytope lens. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.12312v1-abstract-full').style.display = 'none'; document.getElementById('2211.12312v1-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 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">22/11/22 initial upload</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.06745">arXiv:2204.06745</a> <span> [<a href="https://arxiv.org/pdf/2204.06745">pdf</a>, <a href="https://arxiv.org/format/2204.06745">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> GPT-NeoX-20B: An Open-Source Autoregressive Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Black%2C+S">Sid Black</a>, <a href="/search/cs?searchtype=author&query=Biderman%2C+S">Stella Biderman</a>, <a href="/search/cs?searchtype=author&query=Hallahan%2C+E">Eric Hallahan</a>, <a href="/search/cs?searchtype=author&query=Anthony%2C+Q">Quentin Anthony</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Leo Gao</a>, <a href="/search/cs?searchtype=author&query=Golding%2C+L">Laurence Golding</a>, <a href="/search/cs?searchtype=author&query=He%2C+H">Horace He</a>, <a href="/search/cs?searchtype=author&query=Leahy%2C+C">Connor Leahy</a>, <a href="/search/cs?searchtype=author&query=McDonell%2C+K">Kyle McDonell</a>, <a href="/search/cs?searchtype=author&query=Phang%2C+J">Jason Phang</a>, <a href="/search/cs?searchtype=author&query=Pieler%2C+M">Michael Pieler</a>, <a href="/search/cs?searchtype=author&query=Prashanth%2C+U+S">USVSN Sai Prashanth</a>, <a href="/search/cs?searchtype=author&query=Purohit%2C+S">Shivanshu Purohit</a>, <a href="/search/cs?searchtype=author&query=Reynolds%2C+L">Laria Reynolds</a>, <a href="/search/cs?searchtype=author&query=Tow%2C+J">Jonathan Tow</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Ben Wang</a>, <a href="/search/cs?searchtype=author&query=Weinbach%2C+S">Samuel Weinbach</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="2204.06745v1-abstract-short" style="display: inline;"> We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense autoregressive model that has publicly available weights at the time of submission. In this work, we describe \model{}'s architecture and trainin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.06745v1-abstract-full').style.display = 'inline'; document.getElementById('2204.06745v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.06745v1-abstract-full" style="display: none;"> We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense autoregressive model that has publicly available weights at the time of submission. In this work, we describe \model{}'s architecture and training and evaluate its performance on a range of language-understanding, mathematics, and knowledge-based tasks. We find that GPT-NeoX-20B is a particularly powerful few-shot reasoner and gains far more in performance when evaluated five-shot than similarly sized GPT-3 and FairSeq models. We open-source the training and evaluation code, as well as the model weights, at https://github.com/EleutherAI/gpt-neox. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.06745v1-abstract-full').style.display = 'none'; document.getElementById('2204.06745v1-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 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">To appear in the Proceedings of the ACL Workshop on Challenges & Perspectives in Creating Large Language Models</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.06823">arXiv:2203.06823</a> <span> [<a href="https://arxiv.org/pdf/2203.06823">pdf</a>, <a href="https://arxiv.org/format/2203.06823">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"> SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Desai%2C+A+D">Arjun D Desai</a>, <a href="/search/cs?searchtype=author&query=Schmidt%2C+A+M">Andrew M Schmidt</a>, <a href="/search/cs?searchtype=author&query=Rubin%2C+E+B">Elka B Rubin</a>, <a href="/search/cs?searchtype=author&query=Sandino%2C+C+M">Christopher M Sandino</a>, <a href="/search/cs?searchtype=author&query=Black%2C+M+S">Marianne S Black</a>, <a href="/search/cs?searchtype=author&query=Mazzoli%2C+V">Valentina Mazzoli</a>, <a href="/search/cs?searchtype=author&query=Stevens%2C+K+J">Kathryn J Stevens</a>, <a href="/search/cs?searchtype=author&query=Boutin%2C+R">Robert Boutin</a>, <a href="/search/cs?searchtype=author&query=R%C3%A9%2C+C">Christopher R茅</a>, <a href="/search/cs?searchtype=author&query=Gold%2C+G+E">Garry E Gold</a>, <a href="/search/cs?searchtype=author&query=Hargreaves%2C+B+A">Brian A Hargreaves</a>, <a href="/search/cs?searchtype=author&query=Chaudhari%2C+A+S">Akshay S Chaudhari</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="2203.06823v1-abstract-short" style="display: inline;"> Magnetic resonance imaging (MRI) is a cornerstone of modern medical imaging. However, long image acquisition times, the need for qualitative expert analysis, and the lack of (and difficulty extracting) quantitative indicators that are sensitive to tissue health have curtailed widespread clinical and research studies. While recent machine learning methods for MRI reconstruction and analysis have sh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06823v1-abstract-full').style.display = 'inline'; document.getElementById('2203.06823v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.06823v1-abstract-full" style="display: none;"> Magnetic resonance imaging (MRI) is a cornerstone of modern medical imaging. However, long image acquisition times, the need for qualitative expert analysis, and the lack of (and difficulty extracting) quantitative indicators that are sensitive to tissue health have curtailed widespread clinical and research studies. While recent machine learning methods for MRI reconstruction and analysis have shown promise for reducing this burden, these techniques are primarily validated with imperfect image quality metrics, which are discordant with clinically-relevant measures that ultimately hamper clinical deployment and clinician trust. To mitigate this challenge, we present the Stanford Knee MRI with Multi-Task Evaluation (SKM-TEA) dataset, a collection of quantitative knee MRI (qMRI) scans that enables end-to-end, clinically-relevant evaluation of MRI reconstruction and analysis tools. This 1.6TB dataset consists of raw-data measurements of ~25,000 slices (155 patients) of anonymized patient MRI scans, the corresponding scanner-generated DICOM images, manual segmentations of four tissues, and bounding box annotations for sixteen clinically relevant pathologies. We provide a framework for using qMRI parameter maps, along with image reconstructions and dense image labels, for measuring the quality of qMRI biomarker estimates extracted from MRI reconstruction, segmentation, and detection techniques. Finally, we use this framework to benchmark state-of-the-art baselines on this dataset. We hope our SKM-TEA dataset and code can enable a broad spectrum of research for modular image reconstruction and image analysis in a clinically informed manner. Dataset access, code, and benchmarks are available at https://github.com/StanfordMIMI/skm-tea. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06823v1-abstract-full').style.display = 'none'; document.getElementById('2203.06823v1-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">Accepted to NeurIPS Datasets & Benchmarks (2021)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.06060">arXiv:2203.06060</a> <span> [<a href="https://arxiv.org/pdf/2203.06060">pdf</a>, <a href="https://arxiv.org/format/2203.06060">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"> ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Boone%2C+L">Lyndon Boone</a>, <a href="/search/cs?searchtype=author&query=Biparva%2C+M">Mahdi Biparva</a>, <a href="/search/cs?searchtype=author&query=Forooshani%2C+P+M">Parisa Mojiri Forooshani</a>, <a href="/search/cs?searchtype=author&query=Ramirez%2C+J">Joel Ramirez</a>, <a href="/search/cs?searchtype=author&query=Masellis%2C+M">Mario Masellis</a>, <a href="/search/cs?searchtype=author&query=Bartha%2C+R">Robert Bartha</a>, <a href="/search/cs?searchtype=author&query=Symons%2C+S">Sean Symons</a>, <a href="/search/cs?searchtype=author&query=Strother%2C+S">Stephen Strother</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S+E">Sandra E. Black</a>, <a href="/search/cs?searchtype=author&query=Heyn%2C+C">Chris Heyn</a>, <a href="/search/cs?searchtype=author&query=Martel%2C+A+L">Anne L. Martel</a>, <a href="/search/cs?searchtype=author&query=Swartz%2C+R+H">Richard H. Swartz</a>, <a href="/search/cs?searchtype=author&query=Goubran%2C+M">Maged Goubran</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="2203.06060v1-abstract-short" style="display: inline;"> Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06060v1-abstract-full').style.display = 'inline'; document.getElementById('2203.06060v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.06060v1-abstract-full" style="display: none;"> Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new and existing models to specific distribution shifts in MRI, and accessible multi-site benchmarking datasets are still scarce or task-specific. To address these limitations, we propose ROOD-MRI: a platform for benchmarking the Robustness of DNNs to Out-Of-Distribution (OOD) data, corruptions, and artifacts in MRI. The platform provides modules for generating benchmarking datasets using transforms that model distribution shifts in MRI, implementations of newly derived benchmarking metrics for image segmentation, and examples for using the methodology with new models and tasks. We apply our methodology to hippocampus, ventricle, and white matter hyperintensity segmentation in several large studies, providing the hippocampus dataset as a publicly available benchmark. By evaluating modern DNNs on these datasets, we demonstrate that they are highly susceptible to distribution shifts and corruptions in MRI. We show that while data augmentation strategies can substantially improve robustness to OOD data for anatomical segmentation tasks, modern DNNs using augmentation still lack robustness in more challenging lesion-based segmentation tasks. We finally benchmark U-Nets and transformer-based models, finding consistent differences in robustness to particular classes of transforms across architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.06060v1-abstract-full').style.display = 'none'; document.getElementById('2203.06060v1-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> 11 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">30 pages, 13 figures. For associated GitHub repository, see https://github.com/AICONSlab/roodmri</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.05253">arXiv:2112.05253</a> <span> [<a href="https://arxiv.org/pdf/2112.05253">pdf</a>, <a href="https://arxiv.org/format/2112.05253">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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eichenberg%2C+C">Constantin Eichenberg</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sidney Black</a>, <a href="/search/cs?searchtype=author&query=Weinbach%2C+S">Samuel Weinbach</a>, <a href="/search/cs?searchtype=author&query=Parcalabescu%2C+L">Letitia Parcalabescu</a>, <a href="/search/cs?searchtype=author&query=Frank%2C+A">Anette Frank</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="2112.05253v2-abstract-short" style="display: inline;"> Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling. However, prevailing VL approaches are limited by the requirement for labeled data and the use of complex multi-step pretraining objectives. We present MAGMA - a simple method for augmenting generative language models with additional modalities using adapter-based finetuning. Building on Frozen, we train a series of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.05253v2-abstract-full').style.display = 'inline'; document.getElementById('2112.05253v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.05253v2-abstract-full" style="display: none;"> Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling. However, prevailing VL approaches are limited by the requirement for labeled data and the use of complex multi-step pretraining objectives. We present MAGMA - a simple method for augmenting generative language models with additional modalities using adapter-based finetuning. Building on Frozen, we train a series of VL models that autoregressively generate text from arbitrary combinations of visual and textual input. The pretraining is entirely end-to-end using a single language modeling objective, simplifying optimization compared to previous approaches. Importantly, the language model weights remain unchanged during training, allowing for transfer of encyclopedic knowledge and in-context learning abilities from language pretraining. MAGMA outperforms Frozen on open-ended generative tasks, achieving state of the art results on the OKVQA benchmark and competitive results on a range of other popular VL benchmarks, while pretraining on 0.2% of the number of samples used to train SimVLM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.05253v2-abstract-full').style.display = 'none'; document.getElementById('2112.05253v2-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 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">13 pages, 6 figures, 2 tables. Minor improvements. Accepted at EMNLP 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7; I.4.8; I.5.1 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.02234">arXiv:2108.02234</a> <span> [<a href="https://arxiv.org/pdf/2108.02234">pdf</a>, <a href="https://arxiv.org/format/2108.02234">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> </div> </div> <p class="title is-5 mathjax"> Multi-Branch with Attention Network for Hand-Based Person Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baisa%2C+N+L">Nathanael L. Baisa</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B">Bryan Williams</a>, <a href="/search/cs?searchtype=author&query=Rahmani%2C+H">Hossein Rahmani</a>, <a href="/search/cs?searchtype=author&query=Angelov%2C+P">Plamen Angelov</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sue Black</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="2108.02234v5-abstract-short" style="display: inline;"> In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attentio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.02234v5-abstract-full').style.display = 'inline'; document.getElementById('2108.02234v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.02234v5-abstract-full" style="display: none;"> In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attention) branch to capture global structural information for discriminative feature learning. The attention modules focus on the relevant features of the hand image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. Extensive evaluations on two large multi-ethnic and publicly available hand datasets demonstrate that our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.02234v5-abstract-full').style.display = 'none'; document.getElementById('2108.02234v5-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">arXiv admin note: text overlap with arXiv:2101.05260</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.05746">arXiv:2106.05746</a> <span> [<a href="https://arxiv.org/pdf/2106.05746">pdf</a>, <a href="https://arxiv.org/format/2106.05746">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> </div> </div> <p class="title is-5 mathjax"> The 2021 Hotel-ID to Combat Human Trafficking Competition Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kamath%2C+R">Rashmi Kamath</a>, <a href="/search/cs?searchtype=author&query=Rolwes%2C+G">Gregory Rolwes</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Samuel Black</a>, <a href="/search/cs?searchtype=author&query=Stylianou%2C+A">Abby Stylianou</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="2106.05746v2-abstract-short" style="display: inline;"> Hotel recognition is an important task for human trafficking investigations since victims are often photographed in hotel rooms. Identifying these hotels is vital to trafficking investigations since they can help track down current and future victims who might be taken to the same places. Hotel recognition is a challenging fine grained visual classification task as there can be little similarity b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.05746v2-abstract-full').style.display = 'inline'; document.getElementById('2106.05746v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.05746v2-abstract-full" style="display: none;"> Hotel recognition is an important task for human trafficking investigations since victims are often photographed in hotel rooms. Identifying these hotels is vital to trafficking investigations since they can help track down current and future victims who might be taken to the same places. Hotel recognition is a challenging fine grained visual classification task as there can be little similarity between different rooms within the same hotel, and high similarity between rooms from different hotels (especially if they are from the same chain). Hotel recognition to combat human trafficking poses additional challenges as investigative images are often low quality, contain uncommon camera angles and are highly occluded. Here, we present the 2021 Hotel-ID dataset to help raise awareness for this problem and generate novel approaches. The dataset consists of hotel room images that have been crowd-sourced and uploaded through the TraffickCam mobile application. The quality of these images is similar to investigative images and hence models trained on these images have good chances of accurately narrowing down on the correct hotel. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.05746v2-abstract-full').style.display = 'none'; document.getElementById('2106.05746v2-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">CVPR 2021 Workshop on Fine-Grained Visual Categorization (FGVC)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.05260">arXiv:2101.05260</a> <span> [<a href="https://arxiv.org/pdf/2101.05260">pdf</a>, <a href="https://arxiv.org/format/2101.05260">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> </div> </div> <p class="title is-5 mathjax"> Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baisa%2C+N+L">Nathanael L. Baisa</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+B">Bryan Williams</a>, <a href="/search/cs?searchtype=author&query=Rahmani%2C+H">Hossein Rahmani</a>, <a href="/search/cs?searchtype=author&query=Angelov%2C+P">Plamen Angelov</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sue Black</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="2101.05260v8-abstract-short" style="display: inline;"> In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose ha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05260v8-abstract-full').style.display = 'inline'; document.getElementById('2101.05260v8-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.05260v8-abstract-full" style="display: none;"> In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose hand-based person identification by learning both global and local deep feature representations. Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features. For learning the local (part-level) features, we perform uniform partitioning on the conv-layer in both horizontal and vertical directions. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. We make extensive evaluations on two large multi-ethnic and publicly available hand datasets, demonstrating that our proposed method significantly outperforms competing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05260v8-abstract-full').style.display = 'none'; document.getElementById('2101.05260v8-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.00027">arXiv:2101.00027</a> <span> [<a href="https://arxiv.org/pdf/2101.00027">pdf</a>, <a href="https://arxiv.org/format/2101.00027">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> The Pile: An 800GB Dataset of Diverse Text for Language Modeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+L">Leo Gao</a>, <a href="/search/cs?searchtype=author&query=Biderman%2C+S">Stella Biderman</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Sid Black</a>, <a href="/search/cs?searchtype=author&query=Golding%2C+L">Laurence Golding</a>, <a href="/search/cs?searchtype=author&query=Hoppe%2C+T">Travis Hoppe</a>, <a href="/search/cs?searchtype=author&query=Foster%2C+C">Charles Foster</a>, <a href="/search/cs?searchtype=author&query=Phang%2C+J">Jason Phang</a>, <a href="/search/cs?searchtype=author&query=He%2C+H">Horace He</a>, <a href="/search/cs?searchtype=author&query=Thite%2C+A">Anish Thite</a>, <a href="/search/cs?searchtype=author&query=Nabeshima%2C+N">Noa Nabeshima</a>, <a href="/search/cs?searchtype=author&query=Presser%2C+S">Shawn Presser</a>, <a href="/search/cs?searchtype=author&query=Leahy%2C+C">Connor Leahy</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="2101.00027v1-abstract-short" style="display: inline;"> Recent work has demonstrated that increased training dataset diversity improves general cross-domain knowledge and downstream generalization capability for large-scale language models. With this in mind, we present \textit{the Pile}: an 825 GiB English text corpus targeted at training large-scale language models. The Pile is constructed from 22 diverse high-quality subsets -- both existing and new… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00027v1-abstract-full').style.display = 'inline'; document.getElementById('2101.00027v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.00027v1-abstract-full" style="display: none;"> Recent work has demonstrated that increased training dataset diversity improves general cross-domain knowledge and downstream generalization capability for large-scale language models. With this in mind, we present \textit{the Pile}: an 825 GiB English text corpus targeted at training large-scale language models. The Pile is constructed from 22 diverse high-quality subsets -- both existing and newly constructed -- many of which derive from academic or professional sources. Our evaluation of the untuned performance of GPT-2 and GPT-3 on the Pile shows that these models struggle on many of its components, such as academic writing. Conversely, models trained on the Pile improve significantly over both Raw CC and CC-100 on all components of the Pile, while improving performance on downstream evaluations. Through an in-depth exploratory analysis, we document potentially concerning aspects of the data for prospective users. We make publicly available the code used in its construction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.00027v1-abstract-full').style.display = 'none'; document.getElementById('2101.00027v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.12406">arXiv:2012.12406</a> <span> [<a href="https://arxiv.org/pdf/2012.12406">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="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Thomas%2C+K+A">Kevin A. Thomas</a>, <a href="/search/cs?searchtype=author&query=Krzemi%C5%84ski%2C+D">Dominik Krzemi艅ski</a>, <a href="/search/cs?searchtype=author&query=Kidzi%C5%84ski%2C+%C5%81">艁ukasz Kidzi艅ski</a>, <a href="/search/cs?searchtype=author&query=Paul%2C+R">Rohan Paul</a>, <a href="/search/cs?searchtype=author&query=Rubin%2C+E+B">Elka B. Rubin</a>, <a href="/search/cs?searchtype=author&query=Halilaj%2C+E">Eni Halilaj</a>, <a href="/search/cs?searchtype=author&query=Black%2C+M+S">Marianne S. Black</a>, <a href="/search/cs?searchtype=author&query=Chaudhari%2C+A">Akshay Chaudhari</a>, <a href="/search/cs?searchtype=author&query=Gold%2C+G+E">Garry E. Gold</a>, <a href="/search/cs?searchtype=author&query=Delp%2C+S+L">Scott L. Delp</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="2012.12406v1-abstract-short" style="display: inline;"> Objective: We evaluate a fully-automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin echo (MESE) MRI. We have open sourced this model and corresponding segmentations. Methods: We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.12406v1-abstract-full').style.display = 'inline'; document.getElementById('2012.12406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.12406v1-abstract-full" style="display: none;"> Objective: We evaluate a fully-automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin echo (MESE) MRI. We have open sourced this model and corresponding segmentations. Methods: We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-deep, and anterior-central-posterior boundaries. Subregional T2 values and four-year changes were calculated using a musculoskeletal radiologist's segmentations (Reader 1) and the model's segmentations. These were compared using 28 held out images. A subset of 14 images were also evaluated by a second expert (Reader 2) for comparison. Results: Model segmentations agreed with Reader 1 segmentations with a Dice score of 0.85 +/- 0.03. The model's estimated T2 values for individual subregions agreed with those of Reader 1 with an average Spearman correlation of 0.89 and average mean absolute error (MAE) of 1.34 ms. The model's estimated four-year change in T2 for individual regions agreed with Reader 1 with an average correlation of 0.80 and average MAE of 1.72 ms. The model agreed with Reader 1 at least as closely as Reader 2 agreed with Reader 1 in terms of Dice score (0.85 vs 0.75) and subregional T2 values. Conclusions: We present a fast, fully-automated model for segmentation of MESE MRIs. Assessments of cartilage health using its segmentations agree with those of an expert as closely as experts agree with one another. This has the potential to accelerate osteoarthritis research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.12406v1-abstract-full').style.display = 'none'; document.getElementById('2012.12406v1-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.03283">arXiv:1911.03283</a> <span> [<a href="https://arxiv.org/pdf/1911.03283">pdf</a>, <a href="https://arxiv.org/format/1911.03283">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Composing and Embedding the Words-as-Classifiers Model of Grounded Semantics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Moro%2C+D">Daniele Moro</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S">Stacy Black</a>, <a href="/search/cs?searchtype=author&query=Kennington%2C+C">Casey Kennington</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="1911.03283v1-abstract-short" style="display: inline;"> The words-as-classifiers model of grounded lexical semantics learns a semantic fitness score between physical entities and the words that are used to denote those entities. In this paper, we explore how such a model can incrementally perform composition and how the model can be unified with a distributional representation. For the latter, we leverage the classifier coefficients as an embedding. Fo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.03283v1-abstract-full').style.display = 'inline'; document.getElementById('1911.03283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.03283v1-abstract-full" style="display: none;"> The words-as-classifiers model of grounded lexical semantics learns a semantic fitness score between physical entities and the words that are used to denote those entities. In this paper, we explore how such a model can incrementally perform composition and how the model can be unified with a distributional representation. For the latter, we leverage the classifier coefficients as an embedding. For composition, we leverage the underlying mechanics of three different classifier types (i.e., logistic regression, decision trees, and multi-layer perceptrons) to arrive at a several systematic approaches to composition unique to each classifier including both denotational and connotational methods of composition. We compare these approaches to each other and to prior work in a visual reference resolution task using the refCOCO dataset. Our results demonstrate the need to expand upon existing composition strategies and bring together grounded and distributional representations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.03283v1-abstract-full').style.display = 'none'; document.getElementById('1911.03283v1-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 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </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/1704.07699">arXiv:1704.07699</a> <span> [<a href="https://arxiv.org/pdf/1704.07699">pdf</a>, <a href="https://arxiv.org/format/1704.07699">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> </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/10.1038/s41598-018-19781-5">10.1038/s41598-018-19781-5 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ballerini%2C+L">Lucia Ballerini</a>, <a href="/search/cs?searchtype=author&query=Lovreglio%2C+R">Ruggiero Lovreglio</a>, <a href="/search/cs?searchtype=author&query=Valdes-Hernandez%2C+M+d+C">Maria del C. Valdes-Hernandez</a>, <a href="/search/cs?searchtype=author&query=Ramirez%2C+J">Joel Ramirez</a>, <a href="/search/cs?searchtype=author&query=MacIntosh%2C+B+J">Bradley J. MacIntosh</a>, <a href="/search/cs?searchtype=author&query=Black%2C+S+E">Sandra E. Black</a>, <a href="/search/cs?searchtype=author&query=Wardlaw%2C+J+M">Joanna M. Wardlaw</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="1704.07699v1-abstract-short" style="display: inline;"> Perivascular Spaces (PVS) are a recently recognised feature of Small Vessel Disease (SVD), also indicating neuroinflammation, and are an important part of the brain's circulation and glymphatic drainage system. Quantitative analysis of PVS on Magnetic Resonance Images (MRI) is important for understanding their relationship with neurological diseases. In this work, we propose a segmentation techniq… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1704.07699v1-abstract-full').style.display = 'inline'; document.getElementById('1704.07699v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1704.07699v1-abstract-full" style="display: none;"> Perivascular Spaces (PVS) are a recently recognised feature of Small Vessel Disease (SVD), also indicating neuroinflammation, and are an important part of the brain's circulation and glymphatic drainage system. Quantitative analysis of PVS on Magnetic Resonance Images (MRI) is important for understanding their relationship with neurological diseases. In this work, we propose a segmentation technique based on the 3D Frangi filtering for extraction of PVS from MRI. Based on prior knowledge from neuroradiological ratings of PVS, we used ordered logit models to optimise Frangi filter parameters in response to the variability in the scanner's parameters and study protocols. We optimized and validated our proposed models on two independent cohorts, a dementia sample (N=20) and patients who previously had mild to moderate stroke (N=48). Results demonstrate the robustness and generalisability of our segmentation method. Segmentation-based PVS burden estimates correlated with neuroradiological assessments (Spearman's $蟻$ = 0.74, p $<$ 0.001), suggesting the great potential of our proposed method <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1704.07699v1-abstract-full').style.display = 'none'; document.getElementById('1704.07699v1-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> 25 April, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2017. </p> </li> </ol> <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