A Memory-Efficient Class-Incremental Learning Framework for Remote Sensing Scene Classification via Feature Replay

Most existing deep learning models for remote sensing scene classification (RSSC) adopt an offline learning paradigm, where all classes are jointly optimized on fixed-class datasets. In dynamic real-world scenarios with streaming data and emerging classes, such paradigms are inherently prone to cata...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yunze Wei, Yuhan Liu, Ben Niu, Xiantai Xiang, Jingdun Lin, Yuxin Hu, Yirong Wu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-03-01
coleção:	Remote Sensing
Assuntos:	class-incremental learning catastrophic forgetting remote sensing scene classification
Acesso em linha:	https://www.mdpi.com/2072-4292/18/6/896
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!