Unsupervised Class-Incremental Learning Through Confusion
This addresses the challenge of catastrophic forgetting in continual learning without relying on supervised labels, which is incremental as it builds on existing methods by adapting them to a label-agnostic setting.
The paper tackles the problem of unsupervised class-incremental learning by introducing a novelty detection method that uses network confusion to distinguish between learned and novel classes, achieving enhanced performance across benchmarks like MNIST, SVHN, CIFAR-10, CIFAR-100, and CRIB.
While many works on Continual Learning have shown promising results for mitigating catastrophic forgetting, they have relied on supervised training. To successfully learn in a label-agnostic incremental setting, a model must distinguish between learned and novel classes to properly include samples for training. We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance. The effectiveness of our approach is demonstrated across a set of image classification benchmarks: MNIST, SVHN, CIFAR-10, CIFAR-100, and CRIB.