{"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/label-refinery-improving-imagenet","title":"Label Refinery: Improving ImageNet Classification through Label Progression","arxiv_id":"1805.02641","date":"2018-05-07","proceeding":null,"authors":["Hessam Bagherinezhad","Maxwell Horton","Mohammad Rastegari","Ali Farhadi"],"abstract":"Among the three main components (data, labels, and models) of any supervised\nlearning system, data and models have been the main subjects of active\nresearch. However, studying labels and their properties has received very\nlittle attention. Current principles and paradigms of labeling impose several\nchallenges to machine learning algorithms. Labels are often incomplete,\nambiguous, and redundant. In this paper we study the effects of various\nproperties of labels and introduce the Label Refinery: an iterative procedure\nthat updates the ground truth labels after examining the entire dataset. We\nshow significant gain using refined labels across a wide range of models. Using\na Label Refinery improves the state-of-the-art top-1 accuracy of (1) AlexNet\nfrom 59.3 to 67.2, (2) MobileNet from 70.6 to 73.39, (3) MobileNet-0.25 from\n50.6 to 55.59, (4) VGG19 from 72.7 to 75.46, and (5) Darknet19 from 72.9 to\n74.47.","url_abs":"http://arxiv.org/abs/1805.02641v1","url_pdf":"http://arxiv.org/pdf/1805.02641v1.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":"label-refinery-improving-imagenet","repo_url":"https://github.com/hessamb/label-refinery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"label-refinery-improving-imagenet","repo_url":"https://github.com/HoganZhang/label-refinery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"label-refinery-improving-imagenet","repo_url":"https://github.com/Yang-YiFan/DiracDeltaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"label-refinery-improving-imagenet","repo_url":"https://github.com/chrisqqq123/FA-Dist-EfficientNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.02641","atlas_url":"https://app.syntology.ai/?focus=1805.02641","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":"1805.02641"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.02641\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.02641"},"call":"get_concepts_for_paper(arxiv_id=\"1805.02641\")"}],"by_repo":[{"repo":"hessamb/label-refinery","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"HoganZhang/label-refinery","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Yang-YiFan/DiracDeltaNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1807.11164"],"harvested_for_calls":[{"arxiv_id":"1807.11164","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1807.11164"},"call":"get_harvested_code_for_paper(arxiv_id=\"1807.11164\")"}]},{"repo":"chrisqqq123/FA-Dist-EfficientNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1905.11946"],"harvested_for_calls":[{"arxiv_id":"1905.11946","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.11946"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.11946\")"}]}],"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":"86a0a5b419cff0a0674f784ffa8b82fb68f9bb75efd045b98cede30473de9c98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}