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: | Jinhui Li, Xiaorun Li, Yunfeng Yan |
---|---|
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 |
Similar Items
-
Nearest Neighboring Self-Supervised Learning for Hyperspectral Image Classification
by: Yao Qin, et al.
Published: (2023-03-01) -
THE DELETION OF THE HUMAN AGENT IN ENVIRONMENTAL SCIENCE DISCOURSE: AN ECOLINGUISTIC STUDY
by: Wagma Farooq
Published: (2021-12-01) -
An Unsupervised Band Selection Method via Contrastive Learning for Hyperspectral Images
by: Xiaorun Li, et al.
Published: (2023-11-01) -
Factors Affecting Information Security and the Implementation of Bring Your Own Device (BYOD) Programmes in the Kingdom of Saudi Arabia (KSA)
by: Adel A. Bahaddad, et al.
Published: (2022-12-01) -
Security management of BYOD and cloud environment in Saudi Arabia
by: Khalid Almarhabi, et al.
Published: (2023-01-01)