{"id":81,"date":"2022-12-20T15:18:39","date_gmt":"2022-12-20T15:18:39","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/?page_id=81"},"modified":"2022-12-20T15:18:39","modified_gmt":"2022-12-20T15:18:39","slug":"introduction-2","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","title":{"rendered":"Introduction"},"content":{"rendered":"\n<h2 class=\"has-black-color has-text-color wp-block-heading\"><strong>Abstract<\/strong><\/h2>\n\n\n\n<p><\/p>\n\n\n\n<p>Recently <strong>A<\/strong>ctive <strong>D<\/strong>omain <strong>A<\/strong>daptation (ADA) has seen its emergence to boost performance with actively labeled target samples. However, previous work can only deal with a single target domain yet the performance is unknown when multiple targets are available. In this project, we propose an active training and sampling framework called  ???  to tackle this challenging <strong>M<\/strong>ulti-<strong>T<\/strong>arget <strong>A<\/strong>ctive <strong>D<\/strong>omain <strong>A<\/strong>daptation (MT-ADA) task. In particular,  we leverage the geometric properties of pseudo-gradients in high-dimensional embedding space to select samples beneficial to both classification and domain alignment. We<br>show ??? \u2019s superior performance on a variety of experiments with different labeling budgets, conducted on image domain adaptation datasets Office-31 and Office-Home.<\/p>\n\n\n\n<h2 class=\"has-black-color has-text-color wp-block-heading\"><strong>Motivation<\/strong><\/h2>\n\n\n\n<p><\/p>\n\n\n\n<p>Nowadays, more and more deep-learning-based models are deployed on real-world tasks. However, because of the biased training data domain distribution, there would be performance degradation when testing on different domains, a.k.a domain gap. In this project, we want to bridge the gap and boost cross-domain performance in the training process.<\/p>\n\n\n\n<h2 class=\"has-black-color has-text-color wp-block-heading\"><strong>Problem setting<\/strong><\/h2>\n\n\n\n<p><\/p>\n\n\n\n<p>Suppose that we have a single-domain labeled source dataset <strong>S<\/strong> with k classes and we can access <strong>N <\/strong>multi-domain unlabeled target datasets with the same classes. We aim at training <strong>one<\/strong> image classification model that performs well on all target domains. And we report the average top-1 accuracy across different source domains and all target domains as the evaluation metric.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Abstract Recently Active Domain Adaptation (ADA) has seen its emergence to boost performance with actively labeled target samples. However, previous work can only deal with a single target domain yet the performance is unknown when multiple targets are available. In this project, we propose an active training and sampling framework called ??? to tackle this &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Introduction&#8221;<\/span><\/a><\/p>\n","protected":false},"author":139,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-81","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Introduction - Automatic bias removal from datasets<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Introduction - Automatic bias removal from datasets\" \/>\n<meta property=\"og:description\" content=\"Abstract Recently Active Domain Adaptation (ADA) has seen its emergence to boost performance with actively labeled target samples. However, previous work can only deal with a single target domain yet the performance is unknown when multiple targets are available. In this project, we propose an active training and sampling framework called ??? to tackle this &hellip; Continue reading &quot;Introduction&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/\" \/>\n<meta property=\"og:site_name\" content=\"Automatic bias removal from datasets\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\",\"name\":\"Introduction - Automatic bias removal from datasets\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/#website\"},\"datePublished\":\"2022-12-20T15:18:39+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Introduction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\",\"name\":\"Automatic bias removal from datasets\",\"description\":\"Students: Lin ZHANG, Linghan Xu | Advisor: Fernando De la Torre\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Introduction - Automatic bias removal from datasets","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","og_locale":"en_US","og_type":"article","og_title":"Introduction - Automatic bias removal from datasets","og_description":"Abstract Recently Active Domain Adaptation (ADA) has seen its emergence to boost performance with actively labeled target samples. However, previous work can only deal with a single target domain yet the performance is unknown when multiple targets are available. In this project, we propose an active training and sampling framework called ??? to tackle this &hellip; Continue reading \"Introduction\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","og_site_name":"Automatic bias removal from datasets","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","name":"Introduction - Automatic bias removal from datasets","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/#website"},"datePublished":"2022-12-20T15:18:39+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/"},{"@type":"ListItem","position":2,"name":"Introduction"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/","name":"Automatic bias removal from datasets","description":"Students: Lin ZHANG, Linghan Xu | Advisor: Fernando De la Torre","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages\/81","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/users\/139"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/comments?post=81"}],"version-history":[{"count":6,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages\/81\/revisions"}],"predecessor-version":[{"id":106,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages\/81\/revisions\/106"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/media?parent=81"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}