Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning

arXiv:2405.11067v1 Announce Type: new
Abstract: The primary objective of methods in continual learning is to learn tasks in a sequential manner over time from a stream of data, while mitigating the detrimental phenomenon of catastrophic forgetting. In this paper, we focus on learning an optimal representation between previous class prototypes and newly encountered ones. We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL) tailored specifically for class-incremental learning scenarios. Therefore, we introduce a contrastive loss that incorporates …

abstract arxiv bayesian catastrophic forgetting class continual cs.ai cs.cv data focus incremental incremental learning learn loss paper representation tasks type while