{"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/multiple-instance-detection-network-with","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","arxiv_id":"1704.00138","date":"2017-04-01","proceeding":"CVPR 2017 7","authors":["Peng Tang","Xinggang Wang","Xiang Bai","Wenyu Liu"],"abstract":"Of late, weakly supervised object detection is with great importance in\nobject recognition. Based on deep learning, weakly supervised detectors have\nachieved many promising results. However, compared with fully supervised\ndetection, it is more challenging to train deep network based detectors in a\nweakly supervised manner. Here we formulate weakly supervised detection as a\nMultiple Instance Learning (MIL) problem, where instance classifiers (object\ndetectors) are put into the network as hidden nodes. We propose a novel online\ninstance classifier refinement algorithm to integrate MIL and the instance\nclassifier refinement procedure into a single deep network, and train the\nnetwork end-to-end with only image-level supervision, i.e., without object\nlocation information. More precisely, instance labels inferred from weak\nsupervision are propagated to their spatially overlapped instances to refine\ninstance classifier online. The iterative instance classifier refinement\nprocedure is implemented using multiple streams in deep network, where each\nstream supervises its latter stream. Weakly supervised object detection\nexperiments are carried out on the challenging PASCAL VOC 2007 and 2012\nbenchmarks. We obtain 47% mAP on VOC 2007 that significantly outperforms the\nprevious state-of-the-art.","url_abs":"http://arxiv.org/abs/1704.00138v1","url_pdf":"http://arxiv.org/pdf/1704.00138v1.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":"multiple-instance-detection-network-with","repo_url":"https://github.com/ppengtang/oicr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiple-instance-detection-network-with","repo_url":"https://github.com/jd730/OICR-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multiple-instance-detection-network-with","repo_url":"https://github.com/ppengtang/pcl.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiple-instance-detection-network-with","repo_url":"https://github.com/researchmm/WSOD2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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-recognition","task_name":"Object Recognition"},{"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","task":"Weakly Supervised Object Detection","dataset":"ImageNet","model":"Online Instance Classifier Refinement","rank_in_archive_order":4,"of":4,"metrics":{"MAP":"6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"OICR-Ens + FRCNN","rank_in_archive_order":26,"of":41,"metrics":{"MAP":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2012 test","model":"OICR-Ens + FRCNN","rank_in_archive_order":24,"of":32,"metrics":{"MAP":"42.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.00138","atlas_url":"https://app.syntology.ai/?focus=1704.00138","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":"1704.00138"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.00138\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.00138"},"call":"get_concepts_for_paper(arxiv_id=\"1704.00138\")"}],"by_repo":[{"repo":"ppengtang/oicr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1807.03342"],"harvested_for_calls":[{"arxiv_id":"1807.03342","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1807.03342"},"call":"get_harvested_code_for_paper(arxiv_id=\"1807.03342\")"}]},{"repo":"jd730/OICR-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ppengtang/pcl.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.04725"],"harvested_for_calls":[{"arxiv_id":"2004.04725","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.04725"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.04725\")"}]},{"repo":"researchmm/WSOD2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.04972"],"harvested_for_calls":[{"arxiv_id":"1909.04972","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.04972"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.04972\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"caab514df8457082760f124f5cd86548d6bdd4fd7c16e8e0712acbabad632438","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}