Published on Wed Sep 29 2021

Contrastive Attraction and Contrastive Repulsion for Representation Learning

See More ...

Contrastive learning (CL) methods effectively learn data representations without label supervision, where the encoder needs to contrast each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By leveraging large amounts of unlabeled image data, recent CL methods have achieved promising results when pretrained on ImageNet, a well-curated dataset with balanced image classes. However, they tend to yield worse performance when pretrained on images in the wild. In this paper, to further improve the performance of CL and enhance its robustness on uncurated datasets, we propose a doubly CL strategy that contrasts positive samples and negative ones within themselves separately. We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples. Theoretical analysis reveals that CACR generalizes CL's behavior by positive attraction and negative repulsion. It further considers the intra-contrastive relation within the positive and negative pairs to narrow the gap between the sampled and true distribution, which is important when datasets are less curated. Extensive large-scale experiments on standard vision tasks show that CACR not only consistently outperforms existing CL methods on benchmark datasets in representation learning, but also shows better robustness when generalized to pretrain on wild large image datasets.

0
0
0