Contrastive Regularization for Semi-Supervised Learning

TL;DR

This paper introduces contrastive regularization to enhance semi-supervised learning by promoting well-clustered features, leading to faster, more accurate training and improved performance on benchmarks, including open-set scenarios.

Contribution

It proposes a novel contrastive regularization method that improves consistency regularization by better clustering features, enabling more efficient label propagation and achieving state-of-the-art results.

Findings

Improves semi-supervised learning accuracy and efficiency.

Achieves state-of-the-art results with fewer training iterations.

Robust performance on open-set semi-supervised learning.

Abstract

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.