{"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/dissimilarity-coefficient-based-weakly","title":"Dissimilarity Coefficient based Weakly Supervised Object Detection","arxiv_id":"1811.10016","date":"2018-11-25","proceeding":"CVPR 2019 6","authors":["Aditya Arun","C. V. Jawahar","M. Pawan Kumar"],"abstract":"We consider the problem of weakly supervised object detection, where the\ntraining samples are annotated using only image-level labels that indicate the\npresence or absence of an object category. In order to model the uncertainty in\nthe location of the objects, we employ a dissimilarity coefficient based\nprobabilistic learning objective. The learning objective minimizes the\ndifference between an annotation agnostic prediction distribution and an\nannotation aware conditional distribution. The main computational challenge is\nthe complex nature of the conditional distribution, which consists of terms\nover hundreds or thousands of variables. The complexity of the conditional\ndistribution rules out the possibility of explicitly modeling it. Instead, we\nexploit the fact that deep learning frameworks rely on stochastic optimization.\nThis allows us to use a state of the art discrete generative model that can\nprovide annotation consistent samples from the conditional distribution.\nExtensive experiments on PASCAL VOC 2007 and 2012 data sets demonstrate the\nefficacy of our proposed approach.","url_abs":"http://arxiv.org/abs/1811.10016v1","url_pdf":"http://arxiv.org/pdf/1811.10016v1.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":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"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":"Pred Net (Ens)","rank_in_archive_order":12,"of":41,"metrics":{"MAP":"53.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2012 test","model":"Pred Net (Ens)","rank_in_archive_order":11,"of":32,"metrics":{"MAP":"49.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.10016","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}