Aug 2026
Complementary Asymmetric Representation Learning for Exemplar-Free Class-Incremental Learning
The proposed CARL framework employs two parallel ARL branches and aggregates their Mahalanobis distances during inference to improve prediction performance and is compared with recent methods using three widely recognized datasets.
Run-Hang Chen, Xiao-Yuan Jing, Xiaodong Jia
· ACM Transactions on Multimed... · 0 citations