RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation

arXiv:2309.10479v2 Announce Type: replace
Abstract: Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed. In this paper, we extend our previous approach (RECALL) and tackle forgetting by exploiting unsupervised web-crawled data to retrieve examples of old classes from online databases. In contrast to the original methodology, which did not incorporate an assessment of web-based data, the present work proposes two …

abstract adversarial arxiv catastrophic forgetting continual cs.cv incremental issue knowledge paper recall regularization segmentation semantic strategies struggle through type unsupervised web