Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning
It addresses the problem of forgetting in continual learning for AI systems, but it is incremental as it builds on existing contrastive and prototypical methods.
The paper tackles catastrophic forgetting in class-incremental learning by proposing a Bayesian learning-driven prototypical contrastive loss (BLCL) to learn effective representations between old and new class prototypes, achieving state-of-the-art results on datasets like CIFAR-10, CIFAR-100, and ImageNet100.
The primary objective of methods in continual learning is to learn tasks in a sequential manner over time (sometimes from a stream of data), while mitigating the detrimental phenomenon of catastrophic forgetting. This paper proposes a method to learn an effective representation between previous and newly encountered class prototypes. We propose a prototypical network with a Bayesian learning-driven contrastive loss (BLCL), tailored specifically for class-incremental learning scenarios. We introduce a contrastive loss that incorporates novel classes into the latent representation by reducing intra-class and increasing inter-class distance. Our approach dynamically adapts the balance between the cross-entropy and contrastive loss functions with a Bayesian learning technique. Experimental results conducted on the CIFAR-10, CIFAR-100, and ImageNet100 datasets for image classification and images of a GNSS-based dataset for interference classification validate the efficacy of our method, showcasing its superiority over existing state-of-the-art approaches. Git: https://gitlab.cc-asp.fraunhofer.de/darcy_gnss/gnss_class_incremental_learning