Prediction Error-based Classification for Class-Incremental Learning

arXiv:2305.18806v2 Announce Type: replace
Abstract: Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class …

abstract arxiv class classification continual cs.ai cs.cv cs.lg error fashion incremental learn prediction stat.ml together type