A Discriminative Spectral-Spatial-Semantic Feature Network Based on Shuffle and Frequency Attention Mechanisms for Hyperspectral Image Classification

Due to end-to-end optimization characteristics and fine generalization ability, convolutional neural networks have been widely applied to hyperspectral image (HSI) classification, playing an irreplaceable role. However, previous studies struggle with two major challenges: (1) HSI contains complex to...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Dongxu Liu, Guangliang Han, Peixun Liu, Hang Yang, Dianbing Chen, Qingqing Li, Jiajia Wu, Yirui Wang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2022-06-01
Colecção:	Remote Sensing
Assuntos:	spectral-spatial-semantic shuffle attention multiscale features frequency attention cross-connected features hyperspectral image classification
Acesso em linha:	https://www.mdpi.com/2072-4292/14/11/2678
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!