Spatial-Channel Multiscale Transformer Network for Hyperspectral Unmixing

In recent years, deep learning (DL) has been demonstrated remarkable capabilities in hyperspectral unmixing (HU) due to its powerful feature representation ability. Convolutional neural networks (CNNs) are effective in capturing local spatial information, but limited in modeling long-range dependenc...

Full description

Bibliographic Details

Published in:	Sensors
Main Authors:	Haixin Sun, Qiuguang Cao, Fanlei Meng, Jingwen Xu, Mengdi Cheng
Format:	Article
Language:	English
Published:	MDPI AG 2025-07-01
Subjects:	global contextual information multiscale transformer hyperspectral unmixing spatial–spectral modeling multi-head self-attention
Online Access:	https://www.mdpi.com/1424-8220/25/14/4493