Co$^2$L: Contrastive Continual Learning
This addresses the problem of forgetting in continual learning for AI systems, offering an incremental improvement over existing methods.
The paper tackles catastrophic forgetting in continual learning by showing that contrastively learned representations are more robust than jointly trained ones, and proposes a rehearsal-based algorithm that achieves state-of-the-art performance on benchmark image classification datasets.
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found that the similar holds in the continual learning con-text: contrastively learned representations are more robust against the catastrophic forgetting than jointly trained representations. Based on this novel observation, we propose a rehearsal-based continual learning algorithm that focuses on continually learning and maintaining transferable representations. More specifically, the proposed scheme (1) learns representations using the contrastive learning objective, and (2) preserves learned representations using a self-supervised distillation step. We conduct extensive experimental validations under popular benchmark image classification datasets, where our method sets the new state-of-the-art performance.