ACAE-REMIND for Online Continual Learning with Compressed Feature Replay

TL;DR

This paper introduces ACAE-REMIND, a novel method for online continual learning that uses a compressed feature replay with an auxiliary classifier auto-encoder, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes a high-compression auto-encoder module for feature replay, enabling more exemplars and improved learning in online continual learning scenarios.

Findings

Achieves state-of-the-art performance on ImageNet-Subset, CIFAR100, and CIFAR10.

Uses high compression rates to reduce memory footprint significantly.

Improves task-agnostic continual learning results.

Abstract

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.