REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning

arXiv:2403.13522v1 Announce Type: new
Abstract: Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning without available historical data. Compared with its counterpart (replay-based CIL) that stores historical samples, the EFCIL suffers more from forgetting issues under the exemplar-free constraint. In this paper, inspired by the recently developed analytic learning (AL) based CIL, we propose a representation enhanced analytic learning (REAL) for EFCIL. The REAL constructs a dual-stream base pretraining (DS-BPT) and a representation enhancing distillation (RED) process …

abstract arxiv catastrophic forgetting class cs.cv cs.lg data free historical data incremental paper representation samples stores type