{"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/openmatch-open-set-semi-supervised-learning","title":"OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization","arxiv_id":null,"date":"2021-12-01","proceeding":"NeurIPS 2021 12","authors":["Kuniaki Saito","Donghyun Kim","Kate Saenko"],"abstract":"Semi-supervised learning (SSL) is an effective means to leverage unlabeled data to improve a model’s performance. Typical SSL methods like FixMatch assume that labeled and unlabeled data share the same label space. However, in practice, unlabeled data can contain categories unseen in the labeled set, i.e., outliers, which can significantly harm the performance of SSL algorithms.  To address this problem, we propose a novel Open-set Semi-Supervised Learning (OSSL) approach called OpenMatch.Learning representations of inliers while rejecting outliers is essential for the success of OSSL. To this end, OpenMatch unifies FixMatch with novelty detection based on one-vs-all (OVA) classifiers. The OVA-classifier outputs the confidence score of a sample being an inlier, providing a threshold to detect outliers. Another key contribution is an open-set soft-consistency regularization loss, which enhances the smoothness of the OVA-classifier with respect to input transformations and greatly improves outlier detection. \\ours achieves state-of-the-art performance on three datasets, and even outperforms a fully supervised model in detecting outliers unseen in unlabeled data on CIFAR10. The code is available at \\url{https://github.com/VisionLearningGroup/OP_Match}.  ","url_abs":"http://proceedings.neurips.cc/paper/2021/hash/da11e8cd1811acb79ccf0fd62cd58f86-Abstract.html","url_pdf":"http://proceedings.neurips.cc/paper/2021/file/da11e8cd1811acb79ccf0fd62cd58f86-Paper.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":"openmatch-open-set-semi-supervised-learning","repo_url":"https://github.com/VisionLearningGroup/OP_Match","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"fixmatch","method_name":"FixMatch"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-37","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 100 Labels (OpenSet, 6/4)","model":"OpenMatch","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"92.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-38","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 400 Labels (OpenSet, 6/4)","model":"OpenMatch","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"94.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-36","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 50 Labels (OpenSet, 6/4)","model":"OpenMatch","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"89.6"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}