Data Augmentation and Spectral Structure Features for Limited Samples Hyperspectral Classification

For both traditional classification and current popular deep learning methods, the limited sample classification problem is very challenging, and the lack of samples is an important factor affecting the classification performance. Our work includes two aspects. First, the unsupervised data augmentat...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Wenning Wang, Xuebin Liu, Xuanqin Mou
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2021-02-01
coleção:	Remote Sensing
Assuntos:	hyperspectral classification data augmentation structural features small sample classification
Acesso em linha:	https://www.mdpi.com/2072-4292/13/4/547
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!