Papers › SimMatch: Semi-supervised Learning with Similarity Matching

SimMatch: Semi-supervised Learning with Similarity Matching

14 Mar 2022CVPR 2022 1arXiv:2203.06915archive 2025-07-28

Mingkai Zheng, Shan You, Lang Huang, Fei Wang, Chen Qian, Chang Xu

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kylezheng1997/simmatch officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic SimilaritySemantic Textual SimilaritySemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification CIFAR-10, 250 Labels SimMatch Percentage error 4.84 #11 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 40 Labels SimMatch Percentage error 5.6 #8 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels SimMatch Percentage error 3.96 #6 of 49 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 2500 Labels SimMatch Percentage error 25.07 #5 of 16 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels SimMatch Percentage error 37.81 #8 of 21 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimMatch (ResNet-50) Top 1 Accuracy 67.2% #27 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimMatch (ResNet-50) Top 1 Accuracy 74.4% #29 of 75 Archive leaderboard report
Semi-Supervised Image Classification cifar-100, 10000 Labels SimMatch Percentage error 20.58 #5 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections