{"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/simmatchv2-semi-supervised-learning-with","title":"SimMatchV2: Semi-Supervised Learning with Graph Consistency","arxiv_id":"2308.06692","date":"2023-08-13","proceeding":"ICCV 2023 1","authors":["Mingkai Zheng","Shan You","Lang Huang","Chen Luo","Fei Wang","Chen Qian","Chang Xu"],"abstract":"Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor. In this paper, we introduce a new semi-supervised learning algorithm - SimMatchV2, which formulates various consistency regularizations between labeled and unlabeled data from the graph perspective. In SimMatchV2, we regard the augmented view of a sample as a node, which consists of a label and its corresponding representation. Different nodes are connected with the edges, which are measured by the similarity of the node representations. Inspired by the message passing and node classification in graph theory, we propose four types of consistencies, namely 1) node-node consistency, 2) node-edge consistency, 3) edge-edge consistency, and 4) edge-node consistency. We also uncover that a simple feature normalization can reduce the gaps of the feature norm between different augmented views, significantly improving the performance of SimMatchV2. Our SimMatchV2 has been validated on multiple semi-supervised learning benchmarks. Notably, with ResNet-50 as our backbone and 300 epochs of training, SimMatchV2 achieves 71.9\\% and 76.2\\% Top-1 Accuracy with 1\\% and 10\\% labeled examples on ImageNet, which significantly outperforms the previous methods and achieves state-of-the-art performance. Code and pre-trained models are available at \\href{https://github.com/mingkai-zheng/SimMatchV2}{https://github.com/mingkai-zheng/SimMatchV2}.","url_abs":"https://arxiv.org/abs/2308.06692v1","url_pdf":"https://arxiv.org/pdf/2308.06692v1.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":"simmatchv2-semi-supervised-learning-with","repo_url":"https://github.com/mingkai-zheng/simmatchv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simmatchv2-semi-supervised-learning-with","repo_url":"https://github.com/kylezheng1997/simmatch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SimMatchV2 (ResNet-50)","rank_in_archive_order":15,"of":65,"metrics":{"Top 1 Accuracy":"71.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SimMatchV2 (ResNet-50)","rank_in_archive_order":23,"of":75,"metrics":{"Top 1 Accuracy":"76.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.06692","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}