i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Understand

Contrastive representation learning has shown to be effective to learn representations from unlabeled data.

• However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge.
• In this work, we propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning.
• We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch.