Class incremental learning with self-supervised pre-training and prototype learning

Wenzhuo Liu, Xin-Jian Wu, Fei Zhu, Ming-Ming Yu, Chuang Wang, Cheng-Lin Liu

Abstract: Highlights•A two-stage framework for class incremental learning (CIL) with a pre-trained feature encoder yielding high intrinsic dimensionality is proposed.•An Incremental Prototype Classifier (IPC) is used to address classifier distortion.•Our non-exemplar-based method outperforms state-of-the-art CIL methods.