{"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-localization-using-deep","title":"Weakly Supervised Localization using Deep Feature Maps","arxiv_id":"1603.00489","date":"2016-03-01","proceeding":null,"authors":["Archith J. Bency","Heesung Kwon","Hyungtae Lee","S. Karthikeyan","B. S. Manjunath"],"abstract":"Object localization is an important computer vision problem with a variety of\napplications. The lack of large scale object-level annotations and the relative\nabundance of image-level labels makes a compelling case for weak supervision in\nthe object localization task. Deep Convolutional Neural Networks are a class of\nstate-of-the-art methods for the related problem of object recognition. In this\npaper, we describe a novel object localization algorithm which uses\nclassification networks trained on only image labels. This weakly supervised\nmethod leverages local spatial and semantic patterns captured in the\nconvolutional layers of classification networks. We propose an efficient beam\nsearch based approach to detect and localize multiple objects in images. The\nproposed method significantly outperforms the state-of-the-art in standard\nobject localization data-sets with a 8 point increase in mAP scores.","url_abs":"http://arxiv.org/abs/1603.00489v2","url_pdf":"http://arxiv.org/pdf/1603.00489v2.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":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-coco","task":"Weakly Supervised Object Detection","dataset":"COCO (Common Objects in Context)","model":"Deep Feature Maps","rank_in_archive_order":4,"of":5,"metrics":{"MAP":"47.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}