{"id":89,"date":"2022-12-20T15:16:04","date_gmt":"2022-12-20T15:16:04","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/?page_id=89"},"modified":"2022-12-20T15:34:35","modified_gmt":"2022-12-20T15:34:35","slug":"experiments-2","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/","title":{"rendered":"Experiments"},"content":{"rendered":"\n<p>We conduct experiments on two different domain adaptation benchmarks, i.e. Office-31<sup>[1] <\/sup>and Office-home<sup>[2]<\/sup>, to show the superior performance of our methods. Since Office-31 is a relatively small dataset, we label 30 images in each active learning stage. As for Office-home, we label 1% of unlabeled data in each stage. First, we compare with the pure-score-based sampling strategies where we directly choose samples with the highest acquisition scores (best performance highlighted in bold). The result shows that our proposed methods consistently outperform entropy, a widely used uncertainty estimator. In addition, we also modify CLUE, which is a state-of-the-art method considering both uncertainty and diversity, based on our proposed score. The model surpasses CLUE ~1% on average top-1 accuracy in the early stages, which suggests that we need to consider both classification and domain alignment in the sampling process.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-1024x640.png\" alt=\"\" class=\"wp-image-97\" width=\"674\" height=\"421\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-1024x640.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-300x187.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-768x480.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1.png 1226w\" sizes=\"auto, (max-width: 674px) 100vw, 674px\" \/><figcaption>Experiment results on Office-31 dataset.<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"641\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-2-1024x641.png\" alt=\"\" class=\"wp-image-98\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-2-1024x641.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-2-300x188.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-2-768x481.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-2.png 1226w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Experiment results on Office-home dataset.<\/figcaption><\/figure>\n\n\n\n<p class=\"has-small-font-size\">[1] Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. Adapting visual category models to new domains. In ECCV, 2010. <\/p>\n\n\n\n<p class=\"has-small-font-size\">[2] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Panchanathan. Deep hashing network for unsupervised domain adaptation. In CVPR, 2017.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We conduct experiments on two different domain adaptation benchmarks, i.e. Office-31[1] and Office-home[2], to show the superior performance of our methods. Since Office-31 is a relatively small dataset, we label 30 images in each active learning stage. As for Office-home, we label 1% of unlabeled data in each stage. First, we compare with the pure-score-based &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Experiments&#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-89","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Experiments - 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\/experiments-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Experiments - Automatic bias removal from datasets\" \/>\n<meta property=\"og:description\" content=\"We conduct experiments on two different domain adaptation benchmarks, i.e. Office-31[1] and Office-home[2], to show the superior performance of our methods. Since Office-31 is a relatively small dataset, we label 30 images in each active learning stage. As for Office-home, we label 1% of unlabeled data in each stage. First, we compare with the pure-score-based &hellip; Continue reading &quot;Experiments&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/\" \/>\n<meta property=\"og:site_name\" content=\"Automatic bias removal from datasets\" \/>\n<meta property=\"article:modified_time\" content=\"2022-12-20T15:34:35+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-1024x640.png\" \/>\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\\\/experiments-2\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/\",\"name\":\"Experiments - Automatic bias removal from datasets\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/wp-content\\\/uploads\\\/sites\\\/59\\\/2022\\\/12\\\/image-1-1024x640.png\",\"datePublished\":\"2022-12-20T15:16:04+00:00\",\"dateModified\":\"2022-12-20T15:34:35+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/wp-content\\\/uploads\\\/sites\\\/59\\\/2022\\\/12\\\/image-1.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/wp-content\\\/uploads\\\/sites\\\/59\\\/2022\\\/12\\\/image-1.png\",\"width\":1226,\"height\":766},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/experiments-2\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team4\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Experiments\"}]},{\"@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":"Experiments - 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\/experiments-2\/","og_locale":"en_US","og_type":"article","og_title":"Experiments - Automatic bias removal from datasets","og_description":"We conduct experiments on two different domain adaptation benchmarks, i.e. Office-31[1] and Office-home[2], to show the superior performance of our methods. Since Office-31 is a relatively small dataset, we label 30 images in each active learning stage. As for Office-home, we label 1% of unlabeled data in each stage. First, we compare with the pure-score-based &hellip; Continue reading \"Experiments\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/","og_site_name":"Automatic bias removal from datasets","article_modified_time":"2022-12-20T15:34:35+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-1024x640.png","type":"","width":"","height":""}],"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\/experiments-2\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/","name":"Experiments - Automatic bias removal from datasets","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1-1024x640.png","datePublished":"2022-12-20T15:16:04+00:00","dateModified":"2022-12-20T15:34:35+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-content\/uploads\/sites\/59\/2022\/12\/image-1.png","width":1226,"height":766},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/experiments-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/"},{"@type":"ListItem","position":2,"name":"Experiments"}]},{"@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\/89","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=89"}],"version-history":[{"count":3,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages\/89\/revisions"}],"predecessor-version":[{"id":99,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/pages\/89\/revisions\/99"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team4\/wp-json\/wp\/v2\/media?parent=89"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}