Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Contrastive Regularization for Semi-Supervised Learning

About

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency regularization restricts the propagation of labeling information due to the exclusion of samples with unconfident pseudo-labels in the model updates. Then, we propose contrastive regularization to improve both efficiency and accuracy of the consistency regularization by well-clustered features of unlabeled data. In specific, after strongly augmented samples are assigned to clusters by their pseudo-labels, our contrastive regularization updates the model so that the features with confident pseudo-labels aggregate the features in the same cluster, while pushing away features in different clusters. As a result, the information of confident pseudo-labels can be effectively propagated into more unlabeled samples during training by the well-clustered features. On benchmarks of semi-supervised learning tasks, our contrastive regularization improves the previous consistency-based methods and achieves state-of-the-art results, especially with fewer training iterations. Our method also shows robust performance on open-set semi-supervised learning where unlabeled data includes out-of-distribution samples.

Doyup Lee, Sungwoong Kim, Ildoo Kim, Yeongjae Cheon, Minsu Cho, Wook-Shin Han• 2022

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy78.97
3518
Image ClassificationCIFAR-10 (test)
Accuracy96.68
3381
Image ClassificationSVHN (test)
Accuracy98.11
362
Image ClassificationImageNet 10% labels (test)--
11
Image ClassificationSTL-10 1,000 labels (test)
Accuracy93.04
2
Image ClassificationImageNet 1% labels (test)
Top-1 Accuracy57.77
2
Showing 6 of 6 rows

Other info

Follow for update