{"id":163190,"date":"2012-01-01T00:00:00","date_gmt":"2012-01-01T00:00:00","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/msr-research-item\/unsupervised-object-class-discovery-via-saliency-guided-multiple-class-learning\/"},"modified":"2018-10-16T21:41:49","modified_gmt":"2018-10-17T04:41:49","slug":"unsupervised-object-class-discovery-via-saliency-guided-multiple-class-learning","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/unsupervised-object-class-discovery-via-saliency-guided-multiple-class-learning\/","title":{"rendered":"Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Discovering object classes from images in a fully unsupervised<br \/>\nway is an intrinsically ambiguous task; saliency<br \/>\ndetection approaches however ease the burden on unsupervised<br \/>\nlearning. We develop an algorithm for simultaneously<br \/>\nlocalizing objects and discovering object classes<br \/>\nvia bottom-up (saliency-guided) multiple class learning<br \/>\n(bMCL), and make the following contributions: (1) saliency<br \/>\ndetection is adopted to convert unsupervised learning into<br \/>\nmultiple instance learning, formulated as bottom-up multiple<br \/>\nclass learning (bMCL); (2) we utilize the Discriminative<br \/>\nEM (DiscEM) to solve our bMCL problem and show<br \/>\nDiscEM\u2019s connection to the MIL-Boost method[34]; (3) localizing<br \/>\nobjects, discovering object classes, and training<br \/>\nobject detectors are performed simultaneously in an integrated<br \/>\nframework; (4) significant improvements over the<br \/>\nexisting methods for multi-class object discovery are observed.<br \/>\nIn addition, we show single class localization as<br \/>\na special case in our bMCL framework and we also demonstrate<br \/>\nthe advantage of bMCL over purely data-driven<br \/>\nsaliency methods.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Discovering object classes from images in a fully unsupervised way is an intrinsically ambiguous task; saliency detection approaches however ease the burden on unsupervised learning. We develop an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL), and make the following contributions: (1) saliency detection is adopted to [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"Computer Vision and Pattern Recognition (CVPR)","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"Computer Vision and Pattern Recognition (CVPR)","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2012-01-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":2012,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-163190","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"","msr_edition":"Computer Vision and Pattern Recognition (CVPR)","msr_affiliation":"","msr_published_date":"2012-01-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"219742","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"cvpr12_multipleclasslearning.pdf","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2012\/01\/cvpr12_multipleclasslearning.pdf","id":219742,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":219742,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2012\/01\/cvpr12_multipleclasslearning.pdf"}],"msr-author-ordering":[{"type":"text","value":"Jun-Yan Zhu","user_id":0,"rest_url":false},{"type":"text","value":"Jiajun Wu","user_id":0,"rest_url":false},{"type":"text","value":"Yan Xu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"echang","user_id":31709,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=echang"},{"type":"text","value":"Zhuowen Tu","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[170702],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":170702,"post_title":"eHuatuo: Teaching Computer to Read Medical Records","post_name":"ehuatuo-teaching-computer-to-read-medical-records","post_type":"msr-project","post_date":"2011-04-10 20:16:13","post_modified":"2019-05-16 04:27:03","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/ehuatuo-teaching-computer-to-read-medical-records\/","post_excerpt":"eHuatuo is an eHealthcare project about Teaching Computer to Read Medical Records developed by Microsoft Research Asia. The goal of the project is to utilize the power of computers to help doctors process the increasing amount of data available in healthcare, ranging from text data, medical imaging data, to genomic data. We aim to link these disparate types of data together for new insights and discoveries. Resources eHuatuo: Teaching Computers to Read Medical Records Dictionary&hellip;","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170702"}]}}]},"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/163190","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/163190\/revisions"}],"predecessor-version":[{"id":538195,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/163190\/revisions\/538195"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=163190"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=163190"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=163190"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=163190"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=163190"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=163190"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=163190"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=163190"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=163190"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=163190"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=163190"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=163190"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=163190"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}