{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/object-discovery-via-contrastive-learning-for","title":"Object Discovery via Contrastive Learning for Weakly Supervised Object Detection","arxiv_id":"2208.07576","date":"2022-08-16","proceeding":null,"authors":["Jinhwan Seo","Wonho Bae","Danica J. Sutherland","Junhyug Noh","Daijin Kim"],"abstract":"Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since weak supervision does not include count or location information, the most common ``argmax'' labeling method often ignores many instances of objects. To alleviate this issue, we propose a novel multiple instance labeling method called object discovery. We further introduce a new contrastive loss under weak supervision where no instance-level information is available for sampling, called weakly supervised contrastive loss (WSCL). WSCL aims to construct a credible similarity threshold for object discovery by leveraging consistent features for embedding vectors in the same class. As a result, we achieve new state-of-the-art results on MS-COCO 2014 and 2017 as well as PASCAL VOC 2012, and competitive results on PASCAL VOC 2007.","url_abs":"https://arxiv.org/abs/2208.07576v2","url_pdf":"https://arxiv.org/pdf/2208.07576v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"object-discovery-via-contrastive-learning-for","repo_url":"https://github.com/jinhseo/od-wscl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"}],"methods":[{"method_slug":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-ms-coco","task":"Weakly Supervised Object Detection","dataset":"MS-COCO-2014","model":"OD-WSCL","rank_in_archive_order":7,"of":7,"metrics":{"AP":"13.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-ms-coco-1","task":"Weakly Supervised Object Detection","dataset":"MS-COCO-2017","model":"OD-WSCL","rank_in_archive_order":1,"of":1,"metrics":{"AP":"13.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"OD-WSCL","rank_in_archive_order":9,"of":41,"metrics":{"MAP":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2012 test","model":"OD-WSCL","rank_in_archive_order":7,"of":32,"metrics":{"MAP":"54.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2208.07576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}