{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/c-mil-continuation-multiple-instance-learning","title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","arxiv_id":"1904.05647","date":"2019-04-11","proceeding":"CVPR 2019 6","authors":["Fang Wan","Chang Liu","Wei Ke","Xiangyang Ji","Jianbin Jiao","Qixiang Ye"],"abstract":"Weakly supervised object detection (WSOD) is a challenging task when provided\nwith image category supervision but required to simultaneously learn object\nlocations and object detectors. Many WSOD approaches adopt multiple instance\nlearning (MIL) and have non-convex loss functions which are prone to get stuck\ninto local minima (falsely localize object parts) while missing full object\nextent during training. In this paper, we introduce a continuation optimization\nmethod into MIL and thereby creating continuation multiple instance learning\n(C-MIL), with the intention of alleviating the non-convexity problem in a\nsystematic way. We partition instances into spatially related and class related\nsubsets, and approximate the original loss function with a series of smoothed\nloss functions defined within the subsets. Optimizing smoothed loss functions\nprevents the training procedure falling prematurely into local minima and\nfacilitates the discovery of Stable Semantic Extremal Regions (SSERs) which\nindicate full object extent. On the PASCAL VOC 2007 and 2012 datasets, C-MIL\nimproves the state-of-the-art of weakly supervised object detection and weakly\nsupervised object localization with large margins.","url_abs":"http://arxiv.org/abs/1904.05647v1","url_pdf":"http://arxiv.org/pdf/1904.05647v1.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":"c-mil-continuation-multiple-instance-learning","repo_url":"https://github.com/Winfrand/C-MIL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"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":"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":"FRCNN C-MIL","rank_in_archive_order":15,"of":41,"metrics":{"MAP":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2012 test","model":"C-MIL","rank_in_archive_order":17,"of":32,"metrics":{"MAP":"46.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.05647","atlas_url":"https://app.syntology.ai/?focus=1904.05647","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1904.05647"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.05647\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.05647"},"call":"get_concepts_for_paper(arxiv_id=\"1904.05647\")"}],"by_repo":[{"repo":"Winfrand/C-MIL","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51b1a51af5a9b32c3d5508b6120d23ec5114359f2de4e8f3a7e1a2c70a80dc7d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}