G-ACIL: Analytic Learning for Exemplar-Free Generalized Class Incremental Learning

arXiv:2403.15706v1 Announce Type: new
Abstract: Class incremental learning (CIL) trains a network on sequential tasks with separated categories but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The generalized CIL (GCIL) aims to address the CIL problem in a more real-world scenario, where incoming data have mixed data categories and unknown sample size distribution, leading to intensified forgetting. Existing attempts for the GCIL either have poor performance, or invade data privacy by saving …

arxiv class cs.cv cs.lg free generalized incremental type