Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
This work addresses a specific bottleneck in contrastive learning for computer vision researchers, offering an incremental but plug-and-play enhancement to existing methods.
The paper tackles the problem of designing effective data augmentation strategies for contrastive learning in self-supervised vision representation learning by introducing JointCrop and JointBlur, which generate more challenging positive pairs using the joint distribution of augmentation parameters, resulting in notable performance improvements across multiple baselines like SimCLR and BYOL.
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by the story of the blind men and the elephant, we introduce JointCrop and JointBlur. These methods generate more challenging positive pairs by leveraging the joint distribution of the two augmentation parameters, thereby enabling contrastive learning to acquire more effective feature representations. To the best of our knowledge, this is the first effort to explicitly incorporate the joint distribution of two data augmentation parameters into contrastive learning. As a plug-and-play framework without additional computational overhead, JointCrop and JointBlur enhance the performance of SimCLR, BYOL, MoCo v1, MoCo v2, MoCo v3, SimSiam, and Dino baselines with notable improvements.