{"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/remixmatch-semi-supervised-learning-with","title":"ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring","arxiv_id":null,"date":"2020-05-01","proceeding":"ICLR 2020 1","authors":["David Berthelot","Nicholas Carlini","Ekin D. Cubuk","Alex Kurakin","Kihyuk Sohn","Han Zhang","Colin Raffel"],"abstract":"We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring.\n- Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels.\n- Augmentation anchoring} feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input.\nTo produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained.\n\nOur new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5 times and 16 times less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4000 examples) and a median accuracy of 84.92% with just four labels per class.\n","url_abs":"https://openreview.net/forum?id=HklkeR4KPB","url_pdf":"https://openreview.net/pdf?id=HklkeR4KPB","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":"remixmatch-semi-supervised-learning-with","repo_url":"https://github.com/google-research/remixmatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}