Rotation Augmented Distillation for Exemplar-Free Class Incremental Learning with Detailed Analysis

arXiv:2308.15236v2 Announce Type: replace
Abstract: Class incremental learning (CIL) aims to recognize both the old and new classes along the increment tasks. Deep neural networks in CIL suffer from catastrophic forgetting and some approaches rely on saving exemplars from previous tasks, known as the exemplar-based setting, to alleviate this problem. On the contrary, this paper focuses on the Exemplar-Free setting with no old class sample preserved. Balancing the plasticity and stability in deep feature learning with only supervision from new …

abstract analysis arxiv catastrophic forgetting class cs.cv distillation free incremental networks neural networks rotation saving tasks type