{"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/fixmatch-simplifying-semi-supervised-learning-1","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","arxiv_id":null,"date":"2020-01-21","proceeding":null,"authors":["Kihyuk Sohn∗ David Berthelot∗ Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang Colin Raffel"],"abstract":"Semi-supervised learning (SSL) provides an effective\r\nmeans of leveraging unlabeled data to improve a model’s\r\nperformance. In this paper, we demonstrate the power of a\r\nsimple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm,\r\nFixMatch, first generates pseudo-labels using the model’s\r\npredictions on weakly-augmented unlabeled images. For a\r\ngiven image, the pseudo-label is only retained if the model\r\nproduces a high-confidence prediction. The model is then\r\ntrained to predict the pseudo-label when fed a stronglyaugmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10\r\nwith 250 labels and 88.61% accuracy with 40 – just 4 labels per class. Since FixMatch bears many similarities\r\nto existing SSL methods that achieve worse performance,\r\nwe carry out an extensive ablation study to tease apart\r\nthe experimental factors that are most important to FixMatch’s success. We make our code available at https:\r\n//github.com/google-research/fixmatch.","url_abs":"https://arxiv.org/pdf/2001.07685.pdf","url_pdf":"https://arxiv.org/pdf/2001.07685.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":"fixmatch-simplifying-semi-supervised-learning-1","repo_url":"https://github.com/google-research/fixmatch","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[{"method_slug":"fixmatch","method_name":"FixMatch"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"FixMatch (CTA)","rank_in_archive_order":19,"of":117,"metrics":{"Percentage correct":"94.83"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"ReMixMatch","rank_in_archive_order":20,"of":117,"metrics":{"Percentage correct":"94.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"UDA","rank_in_archive_order":28,"of":117,"metrics":{"Percentage correct":"92.34"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"FixMatch (RA)","rank_in_archive_order":30,"of":117,"metrics":{"Percentage correct":"92.02"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"MixMatch","rank_in_archive_order":37,"of":117,"metrics":{"Percentage correct":"89.59"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Mean Teacher","rank_in_archive_order":66,"of":117,"metrics":{"Percentage correct":"78.57"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Π-Model","rank_in_archive_order":82,"of":117,"metrics":{"Percentage correct":"73.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Pseudo-Labeling","rank_in_archive_order":85,"of":117,"metrics":{"Percentage correct":"72.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"google-research/fixmatch","kind":"named_in_paper","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":"89ad5a18aeee273c11ba8e979278bcf3da4f9ae32bb65b02c5d78aa1d5734e59","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}