In Defense of the Learning Without Forgetting for Task Incremental Learning

TL;DR

This paper demonstrates that Learning without Forgetting (LwF), with proper architecture and augmentations, can outperform recent methods in task incremental learning, effectively mitigating catastrophic forgetting over long task sequences.

Contribution

The study shows that LwF's performance can be significantly improved with the right architecture and augmentations, challenging the belief that it fails on long task sequences.

Findings

LwF surpasses recent algorithms in task incremental scenarios.

Proper architecture and augmentations enhance LwF's performance.

Other methods do not benefit as much from similar improvements.

Abstract

Catastrophic forgetting is one of the major challenges on the road for continual learning systems, which are presented with an on-line stream of tasks. The field has attracted considerable interest and a diverse set of methods have been presented for overcoming this challenge. Learning without Forgetting (LwF) is one of the earliest and most frequently cited methods. It has the advantages of not requiring the storage of samples from the previous tasks, of implementation simplicity, and of being well-grounded by relying on knowledge distillation. However, the prevailing view is that while it shows a relatively small amount of forgetting when only two tasks are introduced, it fails to scale to long sequences of tasks. This paper challenges this view, by showing that using the right architecture along with a standard set of augmentations, the results obtained by LwF surpass the latest algorithms for task incremental scenario. This improved performance is demonstrated by an extensive set of experiments over CIFAR-100 and Tiny-ImageNet, where it is also shown that other methods cannot benefit as much from similar improvements.