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

Source: [Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning](<https://www.sota2.com/research/paper/68fa77b71e209131cea74f00>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:50:54.619Z

Authors: Nisha L. Raichur, Lucas Heublein, Tobias Feigl, Alexander R\\"ugamer, Christopher Mutschler, Felix Ott

Published: 2024-05-17T19:49:02.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.11067>)

[PDF](<https://arxiv.org/pdf/2405.11067.pdf>)
