Boosting Contrastive Learning with Relation Knowledge Distillation

TL;DR

This paper introduces a relation-wise contrastive learning approach with relation knowledge distillation to improve lightweight self-supervised models, significantly narrowing the performance gap with supervised methods.

Contribution

It proposes a novel relation-wise contrastive paradigm with a heterogeneous teacher for relation knowledge transfer, addressing semantic collapse in lightweight models.

Findings

Achieves a linear evaluation accuracy of 50.1% on AlexNet, close to supervised performance.

Demonstrates significant improvements across multiple lightweight models.

Provides theoretical analysis supporting the effectiveness of relation-wise contrastive learning.

Abstract

While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast. To address this issue, we propose a relation-wise contrastive paradigm with Relation Knowledge Distillation (ReKD). We introduce a heterogeneous teacher to explicitly mine the semantic information and transferring a novel relation knowledge to the student (lightweight model). The theoretical analysis supports our main concern about instance-wise contrast and verify the effectiveness of our relation-wise contrastive learning. Extensive experimental results also demonstrate that our method achieves significant improvements on multiple lightweight models. Particularly, the linear evaluation on AlexNet obviously improves the current state-of-art from 44.7% to 50.1%, which is the first work to get close to the supervised 50.5%. Code will be made available.