Enhancing Hyperspectral Image Classification With Spectral–Spatial Convolutional FourierKAN Transformer

The dominance of transformer architectures in hyperspectral image (HSI) classification, driven by their self-attention mechanisms and multilayer perceptron (MLP), faces critical challenges in mathematical interpretability and spectral redundancy sensitivity. To address these limitations, we propose...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Zixuan Xue, Zhijing Ye, Boyu Wang, Yuqing Zhang, Chengyong Zheng, Jiangtao Peng
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2026-01-01
coleção:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Assuntos:	Hyperspectral image (HSI) classification Kolmogorov–Arnold network (KAN) multilayer perceptron (MLP) transformer
Acesso em linha:	https://ieeexplore.ieee.org/document/11319177/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!