Effective Decision Boundary Learning for Class Incremental Learning

arXiv:2301.05180v2 Announce Type: replace
Abstract: Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data learning between the learned and new classes because of the limited storage memory. In this work, we present a simple but effective approach to tackle these two factors. First, we employ a re-sampling strategy and Mixup K}nowledge D}istillation (Re-MKD) to improve the …

abstract arxiv class cs.cv cs.lg data decision distillation incremental knowledge memory overfitting storage type