Abstract
The purpose of class-incremental learning is to continually assimilate new classes and preserving the knowledge of learned classes. An important issue is that the learned knowledge would be catastrophically forgotten while the model updated to adapting to new classes. In this paper, we introduce two strategies, Knowledge Bridging and Category Anchoring, to balance the old and new classes. Knowledge Bridging aims to build the semantic correlation of old and new classes, which uses feature-level distillation to apply learned knowledge to new information. Category Anchoring focuses on learning class-specific feature centers that are crucial for distinctively categorizing all classes. Finally, we incorporate the proposed strategies with six prominent class-incremental learning approaches and conduct comprehensive experiments on the CIFAR100 and ImageNetSubset datasets. The results demonstrate that the proposed strategies are helpful to enhancing performance in Class-Incremental Learning (CIL) tasks.