{"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/weakly-supervised-object-boundaries","title":"Weakly Supervised Object Boundaries","arxiv_id":"1511.07803","date":"2015-11-24","proceeding":"CVPR 2016 6","authors":["Anna Khoreva","Rodrigo Benenson","Mohamed Omran","Matthias Hein","Bernt Schiele"],"abstract":"State-of-the-art learning based boundary detection methods require extensive\ntraining data. Since labelling object boundaries is one of the most expensive\ntypes of annotations, there is a need to relax the requirement to carefully\nannotate images to make both the training more affordable and to extend the\namount of training data. In this paper we propose a technique to generate\nweakly supervised annotations and show that bounding box annotations alone\nsuffice to reach high-quality object boundaries without using any\nobject-specific boundary annotations. With the proposed weak supervision\ntechniques we achieve the top performance on the object boundary detection\ntask, outperforming by a large margin the current fully supervised\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1511.07803v1","url_pdf":"http://arxiv.org/pdf/1511.07803v1.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":[],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/edge-detection-on-sbd","task":"Edge Detection","dataset":"SBD","model":"WSOB","rank_in_archive_order":2,"of":2,"metrics":{"Maximum F-measure":"52%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}