{"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/deep-patch-learning-for-weakly-supervised","title":"Deep Patch Learning for Weakly Supervised Object Classification and Discovery","arxiv_id":"1705.02429","date":"2017-05-06","proceeding":null,"authors":["Peng Tang","Xinggang Wang","Zilong Huang","Xiang Bai","Wenyu Liu"],"abstract":"Patch-level image representation is very important for object classification\nand detection, since it is robust to spatial transformation, scale variation,\nand cluttered background. Many existing methods usually require fine-grained\nsupervisions (e.g., bounding-box annotations) to learn patch features, which\nrequires a great effort to label images may limit their potential applications.\nIn this paper, we propose to learn patch features via weak supervisions, i.e.,\nonly image-level supervisions. To achieve this goal, we treat images as bags\nand patches as instances to integrate the weakly supervised multiple instance\nlearning constraints into deep neural networks. Also, our method integrates the\ntraditional multiple stages of weakly supervised object classification and\ndiscovery into a unified deep convolutional neural network and optimizes the\nnetwork in an end-to-end way. The network processes the two tasks object\nclassification and discovery jointly, and shares hierarchical deep features.\nThrough this jointly learning strategy, weakly supervised object classification\nand discovery are beneficial to each other. We test the proposed method on the\nchallenging PASCAL VOC datasets. The results show that our method can obtain\nstate-of-the-art performance on object classification, and very competitive\nresults on object discovery, with faster testing speed than competitors.","url_abs":"http://arxiv.org/abs/1705.02429v1","url_pdf":"http://arxiv.org/pdf/1705.02429v1.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":"deep-patch-learning-for-weakly-supervised","repo_url":"https://github.com/ppengtang/dpl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"ppengtang/dpl","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":"b2bb9a2dfd87c26a01a9bd148e685e86f7ade4a282c01d88277dcc355aada285","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}