Temporal Knowledge Consistency for Unsupervised Visual Representation Learning

TL;DR

This paper introduces Temporal Knowledge Consistency (TKC), a novel method that enhances unsupervised visual representation learning by integrating temporal consistency to reduce noise and catastrophic forgetting in instance discrimination.

Contribution

The paper proposes TKC, which dynamically ensembles and selects temporal knowledge to improve the stability and effectiveness of unsupervised visual learning frameworks.

Findings

TKC improves representation quality on ResNet and AlexNet.

TKC enhances transferability to downstream tasks.

Experimental results demonstrate the effectiveness and generalization of TKC.

Abstract

The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as a supervision signal for the student. The student learns meaningful representations by enforcing instance spatial consistency with the views from the teacher. However, the outputs of the teacher can vary dramatically on the same instance during different training stages, introducing unexpected noise and leading to catastrophic forgetting caused by inconsistent objectives. In this paper, we first integrate instance temporal consistency into current instance discrimination paradigms, and propose a novel and strong algorithm named Temporal Knowledge Consistency (TKC). Specifically, our TKC dynamically ensembles the knowledge of temporal teachers and adaptively selects useful information according to its importance to learning instance temporal consistency. Experimental result shows that TKC can learn better visual representations on both ResNet and AlexNet on linear evaluation protocol while transfer well to downstream tasks. All experiments suggest the good effectiveness and generalization of our method.