Semisupervised hyperspectral image classification based on generative adversarial networks and spectral angle distance
Ying Zhan, Yufeng Wang, Xianchuan Yu · 2023
Read Semisupervised hyperspectral image classification based on generative adversarial networks and spectral angle distance by Ying Zhan, Yufeng Wang, Xianchuan Yu (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10716205.txt.
Description
Ying Zhan, Yufeng Wang, and Xianchuan Yu propose a semisupervised method to classify hyperspectral images, in a 2023 paper. Labeling ground truth for such images is slow and costly, and few training samples make classification hard. Generative adversarial networks can learn from both labeled and unlabeled samples.
Standard cost functions suit ordinary photos, but these images have a simpler one-dimensional spectral structure. The authors add a spectral angle distance as a loss function and fuse features across layers. Since spectral gaps compute quickly with that distance, training converges faster. The method targets land and remote sensing maps where labels are scarce.
Catalog record
| CREATOR | Ying Zhan, Yufeng Wang, Xianchuan Yu |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |