{"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/soft-proposal-networks-for-weakly-supervised","title":"Soft Proposal Networks for Weakly Supervised Object Localization","arxiv_id":"1709.01829","date":"2017-09-06","proceeding":"ICCV 2017 10","authors":["Yi Zhu","Yanzhao Zhou","Qixiang Ye","Qiang Qiu","Jianbin Jiao"],"abstract":"Weakly supervised object localization remains challenging, where only image\nlabels instead of bounding boxes are available during training. Object proposal\nis an effective component in localization, but often computationally expensive\nand incapable of joint optimization with some of the remaining modules. In this\npaper, to the best of our knowledge, we for the first time integrate weakly\nsupervised object proposal into convolutional neural networks (CNNs) in an\nend-to-end learning manner. We design a network component, Soft Proposal (SP),\nto be plugged into any standard convolutional architecture to introduce the\nnearly cost-free object proposal, orders of magnitude faster than\nstate-of-the-art methods. In the SP-augmented CNNs, referred to as Soft\nProposal Networks (SPNs), iteratively evolved object proposals are generated\nbased on the deep feature maps then projected back, and further jointly\noptimized with network parameters, with image-level supervision only. Through\nthe unified learning process, SPNs learn better object-centric filters,\ndiscover more discriminative visual evidence, and suppress background\ninterference, significantly boosting both weakly supervised object localization\nand classification performance. We report the best results on popular\nbenchmarks, including PASCAL VOC, MS COCO, and ImageNet.","url_abs":"http://arxiv.org/abs/1709.01829v1","url_pdf":"http://arxiv.org/pdf/1709.01829v1.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":"soft-proposal-networks-for-weakly-supervised","repo_url":"https://github.com/yeezhu/SPN.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"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"}],"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":"SPNs","rank_in_archive_order":2,"of":5,"metrics":{"MAP":"55.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.01829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}