{"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/mutexmatch-semi-supervised-learning-with-1","title":"MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization","arxiv_id":"2203.14316","date":"2022-03-27","proceeding":null,"authors":["Yue Duan","Zhen Zhao","Lei Qi","Lei Wang","Luping Zhou","Yinghuan Shi","Yang Gao"],"abstract":"The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this paper, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict \"what it is\" by conventional True-Positive Classifier, while the low-confidence samples are employed to achieve a simpler goal -- to predict with ease \"what it is not\" by True-Negative Classifier. In this sense, we not only mitigate the pseudo-labeling errors but also make full use of the low-confidence unlabeled data by consistency of dissimilarity degree. MutexMatch achieves superior performance on multiple benchmark datasets, i.e., CIFAR-10, CIFAR-100, SVHN, STL-10, mini-ImageNet and Tiny-ImageNet. More importantly, our method further shows superiority when the amount of labeled data is scarce, e.g., 92.23% accuracy with only 20 labeled data on CIFAR-10. Our code and model weights have been released at https://github.com/NJUyued/MutexMatch4SSL.","url_abs":"https://arxiv.org/abs/2203.14316v2","url_pdf":"https://arxiv.org/pdf/2203.14316v2.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":"mutexmatch-semi-supervised-learning-with-1","repo_url":"https://github.com/NJUyued/MutexMatch4SSL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-15","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 20 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":1,"of":3,"metrics":{"Percentage error":"7.77"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":10,"of":21,"metrics":{"Percentage error":"5.79"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-16","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 80 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":1,"of":2,"metrics":{"Percentage error":"5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-25","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 200 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"58.41"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-mini-2","task":"Semi-Supervised Image Classification","dataset":"Mini-ImageNet, 1000 Labels","model":"MutexMatch","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"48.04"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":4,"of":15,"metrics":{"Accuracy":"97.47"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-2","task":"Semi-Supervised Image Classification","dataset":"SVHN, 40 Labels","model":"MutexMatch (k=0.6C)","rank_in_archive_order":3,"of":5,"metrics":{"Percentage error":"3.45"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-17","task":"Semi-Supervised Image Classification","dataset":"cifar-10, 10 Labels","model":"MutexMatch","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy (Test)":"76.06"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.14316","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}