H-RNet: Hybrid Relation Network for Few-Shot Learning-Based Hyperspectral Image Classification

Deep network models rely on sufficient training samples to perform reasonably well, which has inevitably constrained their application in classification of hyperspectral images (HSIs) due to the limited availability of labeled data. To tackle this particular challenge, we propose a hybrid relation n...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 15; no. 10; p. 2497
Main Authors Liu, Xiaoyong, Dong, Ziyang, Li, Huihui, Ren, Jinchang, Zhao, Huimin, Li, Hao, Chen, Weiqi, Xiao, Zhanhao
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.05.2023
Subjects
Artificial neural networks
Availability
Classification
Deep learning
few-shot learning
HSI classification
Hyperspectral imaging
Image classification
Learning
Methods
Neural networks
relation network
Remote sensing
Support vector machines
transfer learning
Online AccessGet full text

Cover

More Information
Summary:Deep network models rely on sufficient training samples to perform reasonably well, which has inevitably constrained their application in classification of hyperspectral images (HSIs) due to the limited availability of labeled data. To tackle this particular challenge, we propose a hybrid relation network, H-RNet, by combining three-dimensional (3-D) convolution neural networks (CNN) and two-dimensional (2-D) CNN to extract the spectral–spatial features whilst reducing the complexity of the network. In an end-to-end relation learning module, the sample pairing approach can effectively alleviate the problem of few labeled samples and learn correlations between samples more accurately for more effective classification. Experimental results on three publicly available datasets have fully demonstrated the superior performance of the proposed model in comparison to a few state-of-the-art methods.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15102497