Existing non-example class-incremental learning (NECIL) methods usually utilize a
combination strategy of replay mechanism and knowledge distillation. However, this …

Although deep neural networks exhibit high performance on several specific tasks, they
suffer from a severe issue of catastrophic forgetting when learning new tasks incrementally …

Catastrophic forgetting is the central challenge in class incremental learning (CIL), namely
adapting a model to new data often results in severe performance degradation on previous …