{"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/min-entropy-latent-model-for-weakly","title":"Min-Entropy Latent Model for Weakly Supervised Object Detection","arxiv_id":"1902.06057","date":"2019-02-16","proceeding":"CVPR 2018 6","authors":["Fang Wan","Pengxu Wei","Zhenjun Han","Jianbin Jiao","Qixiang Ye"],"abstract":"Weakly supervised object detection is a challenging task when provided with\nimage category supervision but required to learn, at the same time, object\nlocations and object detectors. The inconsistency between the weak supervision\nand learning objectives introduces significant randomness to object locations\nand ambiguity to detectors. In this paper, a min-entropy latent model (MELM) is\nproposed for weakly supervised object detection. Min-entropy serves as a model\nto learn object locations and a metric to measure the randomness of object\nlocalization during learning. It aims to principally reduce the variance of\nlearned instances and alleviate the ambiguity of detectors. MELM is decomposed\ninto three components including proposal clique partition, object clique\ndiscovery, and object localization. MELM is optimized with a recurrent learning\nalgorithm, which leverages continuation optimization to solve the challenging\nnon-convexity problem. Experiments demonstrate that MELM significantly improves\nthe performance of weakly supervised object detection, weakly supervised object\nlocalization, and image classification, against the state-of-the-art\napproaches.","url_abs":"http://arxiv.org/abs/1902.06057v1","url_pdf":"http://arxiv.org/pdf/1902.06057v1.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":"min-entropy-latent-model-for-weakly","repo_url":"https://github.com/WinFrand/MELM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"weakly-supervised-object-localization","task_name":"Weakly-Supervised Object Localization"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"MELM","rank_in_archive_order":25,"of":41,"metrics":{"MAP":"47.3"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2012 test","model":"MELM","rank_in_archive_order":25,"of":32,"metrics":{"MAP":"42.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.06057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}