MixCo: Mix-up Contrastive Learning for Visual Representation

Understand

Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation.

• By learning to contrast positive pairs' representation from the corresponding negatives pairs, one can train good visual representations without human annotations.
• This paper proposes Mix-up Contrast (MixCo), which extends the contrastive learning concept to semi-positives encoded from the mix-up of positive and negative images.
• MixCo aims to learn the relative similarity of representations, reflecting how much the mixed images have the original positives.