Future-Proofing Class Incremental Learning

arXiv:2404.03200v1 Announce Type: new
Abstract: Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and lower computational costs. However, those methods are highly dependent on the data used to train the feature extractor and may struggle when an insufficient amount of classes are available during the first incremental step. To overcome this limitation, we propose to use …

abstract arxiv attention class computational costs cs.cv cs.lg data feature free future however incremental memory performances train type