{"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/simmatch-semi-supervised-learning-with","title":"SimMatch: Semi-supervised Learning with Similarity Matching","arxiv_id":"2203.06915","date":"2022-03-14","proceeding":"CVPR 2022 1","authors":["Mingkai Zheng","Shan You","Lang Huang","Fei Wang","Chen Qian","Chang Xu"],"abstract":"Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers semantic similarity and instance similarity. In SimMatch, the consistency regularization will be applied on both semantic-level and instance-level. The different augmented views of the same instance are encouraged to have the same class prediction and similar similarity relationship respected to other instances. Next, we instantiated a labeled memory buffer to fully leverage the ground truth labels on instance-level and bridge the gaps between the semantic and instance similarities. Finally, we proposed the \\textit{unfolding} and \\textit{aggregation} operation which allows these two similarities be isomorphically transformed with each other. In this way, the semantic and instance pseudo-labels can be mutually propagated to generate more high-quality and reliable matching targets. Extensive experimental results demonstrate that SimMatch improves the performance of semi-supervised learning tasks across different benchmark datasets and different settings. Notably, with 400 epochs of training, SimMatch achieves 67.2\\%, and 74.4\\% Top-1 Accuracy with 1\\% and 10\\% labeled examples on ImageNet, which significantly outperforms the baseline methods and is better than previous semi-supervised learning frameworks. Code and pre-trained models are available at https://github.com/KyleZheng1997/simmatch.","url_abs":"https://arxiv.org/abs/2203.06915v2","url_pdf":"https://arxiv.org/pdf/2203.06915v2.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":"simmatch-semi-supervised-learning-with","repo_url":"https://github.com/kylezheng1997/simmatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"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-6","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 250 Labels","model":"SimMatch","rank_in_archive_order":11,"of":27,"metrics":{"Percentage error":"4.84"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"SimMatch","rank_in_archive_order":8,"of":21,"metrics":{"Percentage error":"5.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"SimMatch","rank_in_archive_order":6,"of":49,"metrics":{"Percentage error":"3.96"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-9","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 2500 Labels","model":"SimMatch","rank_in_archive_order":5,"of":16,"metrics":{"Percentage error":"25.07"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-8","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 400 Labels","model":"SimMatch","rank_in_archive_order":8,"of":21,"metrics":{"Percentage error":"37.81"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SimMatch (ResNet-50)","rank_in_archive_order":27,"of":65,"metrics":{"Top 1 Accuracy":"67.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SimMatch (ResNet-50)","rank_in_archive_order":29,"of":75,"metrics":{"Top 1 Accuracy":"74.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"SimMatch","rank_in_archive_order":5,"of":29,"metrics":{"Percentage error":"20.58"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.06915","atlas_url":"https://app.syntology.ai/?focus=2203.06915","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}