Self-distilled Knowledge Delegator for Exemplar-free Class Incremental Learning
This addresses the problem of catastrophic forgetting in continual learning for AI systems that cannot store old data, offering a significant improvement over prior exemplar-free methods.
The paper tackles catastrophic forgetting in exemplar-free class incremental learning by introducing a knowledge delegator that transfers knowledge from a previously trained model to a new one using self-distillation to generate samples without old data. It surpasses existing exemplar-free methods by a large margin on four benchmarks, achieving comparable performance to some exemplar-based methods.
Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previously trained classification model to handle the catastrophic forgetting problem in continual learning. Specifically, we introduce a so-called knowledge delegator, which is capable of transferring knowledge from the trained model to a randomly re-initialized new model by generating informative samples. Given the previous model only, the delegator is effectively learned using a self-distillation mechanism in a data-free manner. The knowledge extracted by the delegator is then utilized to maintain the performance of the model on old tasks in incremental learning. This simple incremental learning framework surpasses existing exemplar-free methods by a large margin on four widely used class incremental benchmarks, namely CIFAR-100, ImageNet-Subset, Caltech-101 and Flowers-102. Notably, we achieve comparable performance to some exemplar-based methods without accessing any exemplars.