Abstract
Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data. However, constrained by the limited number of labels, the learned representations of SSL are ambiguous and not distinguishable for inter-class samples. Moreover, the performance of SSL is also largely dependent on the model initialization. To deal with the drawbacks of SSL, in this paper, we propose a novel end-to-end representation learning method, namely ActiveMatch, which combines SSL with contrastive learning and active learning to fully leverage the limited labels. Starting from a small amount of labeled data with unsupervised contrastive learning as a warm-up, ActiveMatch then combines SSL and supervised contrastive learning, and actively selects the most representative samples for labeling during the training, resulting in better representations towards the classification. Compared with MixMatch and FixMatch, we show that ActiveMatch achieves the state-of-the-art performance, with 89.24 accuracy on CIFAR-10 with 100 collected labels, and 92.20 accuracy with 200 collected labels.
Abstract (translated)
URL
https://arxiv.org/abs/2110.02521
