An Ultralightweight Multidomain Feature Extraction Network With Cross Spatial–Spectral Attention for Hyperspectral Image Classification

The combination of convolutional neural networks and attention mechanisms effectively enhances feature representation capabilities in hyperspectral image (HSI) classification. However, most existing methods face great challenges in terms of parameter numbers and computational overhead, which hinders...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Qinggang Wu, Chao Ma, Mengkun He, Zedong Wu, Qinge Wu
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2026-01-01
Saila:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Gaiak:	Cross spatial–spectral attention (CSSA) Gaussian neighbor pixel ReLU (GNReLU) activation hyperspectral image (HSI) classification lightweight networks multidomain feature extraction
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/11303540/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!