Generative binary memory: Pseudo-Replay class-Incremental learning on binarized embeddings

Read full text Summarise with VIRAT
Authors: Yanis Basso-Bert, William Guicquéro, Anca Molnos, Romain Lemaire, Antoine Dupret
Cited by: 0
References: 52

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In dynamic environments where new concepts continuously emerge, Deep Neural Networks (DNNs) must adapt by learning new classes while retaining previously acquired ones. This challenge is addressed by Class-Incremental Learning (CIL). This paper introduces Generative Binary Memory (GBM), a novel CIL pseudo-replay approach which generates synthetic binary pseudo-exemplars. Relying on Bernoulli Mixture Models (BMMs), GBM effectively models the multi-modal characteristics of class distributions, in a latent, binary space. With a specifically-designed feature binarizer, our approach applies to any conventional DNN. GBM also natively supports Binary Neural Networks (BNNs) for highly-constrained model sizes in embedded systems. The experimental results demonstrate that GBM achieves higher than state-of-the-art average accuracy on CIFAR100 (+2.9%) and TinyImageNet (+1.5%) for a ResNet-18 equipped with our binarizer. GBM also outperforms emerging CIL methods for BNNs, with +3.1% in final accuracy and × 4.7 memory reduction, on CORE50.

Fields of Study & Subjects

Domain Adaptation and Few-Shot Learning Advanced Neural Network Applications Data Stream Mining Techniques

Publication details

Journal / source
Neural Networks
Volume
201
Pages
108884–108884
Publication date
21 March 2026
Language
EN