Brain-inspired feature exaggeration in generative replay for continual learning

TL;DR

This paper introduces a brain-inspired feature exaggeration technique using a 'reconstruction repulsion' loss to improve continual learning models, significantly reducing catastrophic forgetting and achieving state-of-the-art results on CIFAR100.

Contribution

It proposes a novel feature exaggeration method inspired by neuroscience, enhancing generative replay in continual learning to better preserve previous knowledge.

Findings

Achieved state-of-the-art performance on CIFAR100 class-incremental learning.

Demonstrated effective reduction of catastrophic forgetting.

Introduced a new 'reconstruction repulsion' loss for feature exaggeration.

Abstract

The catastrophic forgetting of previously learnt classes is one of the main obstacles to the successful development of a reliable and accurate generative continual learning model. When learning new classes, the internal representation of previously learnt ones can often be overwritten, resulting in the model's "memory" of earlier classes being lost over time. Recent developments in neuroscience have uncovered a method through which the brain avoids its own form of memory interference. Applying a targeted exaggeration of the differences between features of similar, yet competing memories, the brain can more easily distinguish and recall them. In this paper, the application of such exaggeration, via the repulsion of replayed samples belonging to competing classes, is explored. Through the development of a 'reconstruction repulsion' loss, this paper presents a new state-of-the-art performance on the classification of early classes in the class-incremental learning dataset CIFAR100.