Unlocking the Potential of Data Augmentation in Contrastive Learning for Hyperspectral Image Classification
Despite the rapid development of deep learning in hyperspectral image classification (HSIC), most models require a large amount of labeled data, which are both time-consuming and laborious to obtain. However, contrastive learning can extract spatial–spectral features from samples without labels, whi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/12/3123 |