CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

• URL: http://arxiv.org/abs/2011.11183v2
• Date: Wed, 3 Mar 2021 01:58:15 GMT
• Title: CoMatch: Semi-supervised Learning with Contrastive Graph Regularization
• Authors: Junnan Li, Caiming Xiong, Steven Hoi
• Abstract summary: CoMatch is a new semi-supervised learning method that unifies dominant approaches. It achieves state-of-the-art performance on multiple datasets.
• Score: 86.84486065798735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of the embeddings through graph-based contrastive learning. CoMatch achieves state-of-the-art performance on multiple datasets. It achieves substantial accuracy improvements on the label-scarce CIFAR-10 and STL-10. On ImageNet with 1% labels, CoMatch achieves a top-1 accuracy of 66.0%, outperforming FixMatch by 12.6%. Furthermore, CoMatch achieves better representation learning performance on downstream tasks, outperforming both supervised learning and self-supervised learning. Code and pre-trained models are available at https://github.com/salesforce/CoMatch.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.