{"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/multi-label-image-classification-via","title":"Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection","arxiv_id":"1809.05884","date":"2018-09-16","proceeding":null,"authors":["Yongcheng Liu","Lu Sheng","Jing Shao","Junjie Yan","Shiming Xiang","Chunhong Pan"],"abstract":"Multi-label image classification is a fundamental but challenging task\ntowards general visual understanding. Existing methods found the region-level\ncues (e.g., features from RoIs) can facilitate multi-label classification.\nNevertheless, such methods usually require laborious object-level annotations\n(i.e., object labels and bounding boxes) for effective learning of the\nobject-level visual features. In this paper, we propose a novel and efficient\ndeep framework to boost multi-label classification by distilling knowledge from\nweakly-supervised detection task without bounding box annotations.\nSpecifically, given the image-level annotations, (1) we first develop a\nweakly-supervised detection (WSD) model, and then (2) construct an end-to-end\nmulti-label image classification framework augmented by a knowledge\ndistillation module that guides the classification model by the WSD model\naccording to the class-level predictions for the whole image and the\nobject-level visual features for object RoIs. The WSD model is the teacher\nmodel and the classification model is the student model. After this cross-task\nknowledge distillation, the performance of the classification model is\nsignificantly improved and the efficiency is maintained since the WSD model can\nbe safely discarded in the test phase. Extensive experiments on two large-scale\ndatasets (MS-COCO and NUS-WIDE) show that our framework achieves superior\nperformances over the state-of-the-art methods on both performance and\nefficiency.","url_abs":"http://arxiv.org/abs/1809.05884v2","url_pdf":"http://arxiv.org/pdf/1809.05884v2.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":"multi-label-image-classification-via","repo_url":"https://github.com/Yochengliu/MLIC-KD-WSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-image-classification","task_name":"Multi-Label Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-classification-on-nus-wide","task":"Multi-Label Classification","dataset":"NUS-WIDE","model":"S-CLs","rank_in_archive_order":9,"of":9,"metrics":{"MAP":"60.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.05884","atlas_url":"https://app.syntology.ai/?focus=1809.05884","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":"1809.05884"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.05884\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.05884"},"call":"get_concepts_for_paper(arxiv_id=\"1809.05884\")"}],"by_repo":[{"repo":"Yochengliu/MLIC-KD-WSD","kind":"listed","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":"272d83eb61abd4dee4fa53ba5018224dfe8bc6df304ec213a19127fd8a4c0ef4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}