Enhancing Visual Continual Learning with Language-Guided Supervision

TL;DR

This paper introduces a novel approach to continual learning by replacing traditional classifier heads with semantic supervision from pretrained language models, improving knowledge transfer and reducing forgetting.

Contribution

It proposes using PLMs to generate semantic class targets, enhancing semantic understanding and transfer in continual visual learning tasks.

Findings

Improves Top-1 accuracy on ImageNet-100 by up to 6.1%.

Reduces forgetting rate significantly across multiple benchmarks.

Seamlessly integrates with existing continual learning methods.

Abstract

Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category name of each class is largely neglected. Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head. We argue that the scarce semantic information conveyed by the one-hot labels hampers the effective knowledge transfer across tasks. In this paper, we revisit the role of the classifier head within the CL paradigm and replace the classifier with semantic knowledge from pretrained language models (PLMs). Specifically, we use PLMs to generate semantic targets for each class, which are frozen and serve as supervision signals during training. Such targets fully consider the semantic correlation between all classes across tasks. Empirical studies show that our approach mitigates forgetting by alleviating representation drifting and facilitating knowledge transfer across tasks. The proposed method is simple to implement and can seamlessly be plugged into existing methods with negligible adjustments. Extensive experiments based on eleven mainstream baselines demonstrate the effectiveness and generalizability of our approach to various protocols. For example, under the class-incremental learning setting on ImageNet-100, our method significantly improves the Top-1 accuracy by 3.2\% to 6.1\% while reducing the forgetting rate by 2.6\% to 13.1\%.