Condensed Prototype Replay for Class Incremental Learning

no code implementations • 25 May 2023 • Jiangtao Kong, Zhenyu Zong, Tianyi Zhou, Huajie Shao

In this paper, we propose YONO that You Only Need to replay One condensed prototype per class, which for the first time can even outperform memory-costly exemplar-replay methods.

Class Incremental Learning Incremental Learning