Adaptive spectral-spatial feature fusion network for hyperspectral image classification using limited training samples

Recently, the excellent power of spectral-spatial feature representation of convolutional neural network (CNN) has gained widespread attention for hyperspectral image (HSI) classification. Nevertheless, the practical performance of CNN-based models in HSI classification is ordinarily limited by the...

Descrición completa

Detalles Bibliográficos

Principais autores:	Hongmin Gao, Zhonghao Chen, Feng Xu
Formato:	Artigo
Idioma:	Inglês
Publicado:	Elsevier 2022-03-01
Series:	International Journal of Applied Earth Observations and Geoinformation
Assuntos:	Convolutional neural network (CNN) Hyperspectral image (HSI) classification Spectral band non-localization (SBNL) Multiscale-share inception block (MSIB) Adaptive feature fusion (AFF)
Acceso en liña:	http://www.sciencedirect.com/science/article/pii/S0303243422000137
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!