This is a code demo for the paper "Open-Set Domain Adaptation for Hyperspectral Image Classification Based on Weighted Generative Adversarial Networks and Dynamic Thresholding". IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2025.3549951.

[1]Ke Bi, Zhaokui Li, Yushi Chen, Qian Du, Li Ma, Yan Wang, Zhuoqun Fang, Mingtai Qi, “Open-Set Domain Adaptation for Hyperspectral Image Classification Based on Weighted Generative Adversarial Networks and Dynamic Thresholding,” IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2025.3549951.

Requirements

python = 3.7.15

torchmetrics = 0.10.3

pytorch = 1.12.1

scikit-learn = 1.0.2

scipy = 1.7.3

You can download the source and target datasets mentioned above at https://pan.baidu.com/s/1BY0EqAWe1BOherY7kZypHQ?pwd=vkde, and move to folder datasets. An example datasets folder has the following structure:

datasets
├── Pavia_7gt
├── PaviaC
├── Houston_7gt
├── Houston18
├── HyRANK
└── Yancheng

Usage:

run main.py