Exemplar-Free Class Incremental Learning via Preserving Class-Discriminative Structure

Exemplar-Free Class Incremental Learning (EFCIL) aims to enable models to learn new classes sequentially without retaining samples from previous tasks. While recent approaches leverage pre-trained models with parameterefficient tuning to mitigate forgetting, they often overlook a crucial cause of forgetting: the collapse of the classdiscriminative structure. This structure comprises two interdependent components: intra-class structure, which characterizes the shape of individual classes, and interclass structure, which characterizes the global geometric relationships among class prototypes. We reveal that catastrophic forgetting stems from the simultaneous deterioration of both intra-class and inter-class structures. To address this, we propose a unified framework that preserves the class-discriminative structure. It preserves the intra-class structure by reshaping class means and covariances to preserve each class's shape during migration, and maintains inter-class structure by stabilizing angular relationships between samples and old prototypes. Extensive experiments demonstrate that our framework outperforms existing leading methods on multiple EFCIL benchmarks, validating that preserving the class-discriminative structure is crucial for mitigating catastrophic forgetting. The code is available at https://github.com/lambor9973/cds.