Towards Non-Exemplar Semi-Supervised Class-Incremental Learning

arXiv:2403.18291v1 Announce Type: new
Abstract: Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize new classes while maintaining the discriminability of old ones. Existing CIL methods have two limitations: a heavy reliance on preserving old data for forgetting mitigation and the need for vast labeled data for knowledge adaptation. To overcome these issues, we propose a non-exemplar semi-supervised CIL …

abstract applications arxiv class cs.cv however incremental learn limitations making networks neural networks novel reliance semi-supervised type world