Defying Imbalanced Forgetting in Class Incremental Learning

arXiv:2403.14910v1 Announce Type: new
Abstract: We observe a high level of imbalance in the accuracy of different classes in the same old task for the first time. This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting. This discovery remains previously unidentified due to the reliance on average incremental accuracy as the measurement for CIL, which assumes that the accuracy of classes …

abstract accuracy arxiv class cs.cv highlights incremental observe type