{"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/progressive-representation-adaptation-for","title":"Progressive Representation Adaptation for Weakly Supervised Object Localization","arxiv_id":"1710.04647","date":"2017-10-12","proceeding":null,"authors":["Dong Li","Jia-Bin Huang","Ya-Li Li","Shengjin Wang","Ming-Hsuan Yang"],"abstract":"We address the problem of weakly supervised object localization where only\nimage-level annotations are available for training object detectors. Numerous\nmethods have been proposed to tackle this problem through mining object\nproposals. However, a substantial amount of noise in object proposals causes\nambiguities for learning discriminative object models. Such approaches are\nsensitive to model initialization and often converge to undesirable local\nminimum solutions. In this paper, we propose to overcome these drawbacks by\nprogressive representation adaptation with two main steps: 1) classification\nadaptation and 2) detection adaptation. In classification adaptation, we\ntransfer a pre-trained network to a multi-label classification task for\nrecognizing the presence of a certain object in an image. Through the\nclassification adaptation step, the network learns discriminative\nrepresentations that are specific to object categories of interest. In\ndetection adaptation, we mine class-specific object proposals by exploiting two\nscoring strategies based on the adapted classification network. Class-specific\nproposal mining helps remove substantial noise from the background clutter and\npotential confusion from similar objects. We further refine these proposals\nusing multiple instance learning and segmentation cues. Using these refined\nobject bounding boxes, we fine-tune all the layer of the classification network\nand obtain a fully adapted detection network. We present detailed experimental\nvalidation on the PASCAL VOC and ILSVRC datasets. Experimental results\ndemonstrate that our progressive representation adaptation algorithm performs\nfavorably against the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1710.04647v1","url_pdf":"http://arxiv.org/pdf/1710.04647v1.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":"progressive-representation-adaptation-for","repo_url":"https://github.com/jbhuang0604/WSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"weakly-supervised-object-localization","task_name":"Weakly-Supervised Object Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.04647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.04647"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jbhuang0604/WSL","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"e7e0093cbca9d12f","entry":"download_image","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e7e0093cbca9d12f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}