CBA: Improving Online Continual Learning via Continual Bias Adaptor
This work addresses the problem of forgetting in continual learning for AI systems, presenting an incremental improvement over existing rehearsal-based methods.
The paper tackles catastrophic forgetting in online continual learning by proposing a Continual Bias Adaptor (CBA) module that adapts the classifier to distribution shifts during training, achieving improved performance with no additional computational cost at test time.
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the previously learned knowledge and biases toward the newly received task. To address this problem, we propose a Continual Bias Adaptor (CBA) module to augment the classifier network to adapt to catastrophic distribution change during training, such that the classifier network is able to learn a stable consolidation of previously learned tasks. In the testing stage, CBA can be removed which introduces no additional computation cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts, and empirically demonstrate its effectiveness through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.