{"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/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":null,"atlas_url":"https://app.syntology.ai/?focus=1805.02641","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}