STMNet (Single-Temporal Mask-Based Network)

Pytorch implementation for STMNet 《STMNet: Single-Temporal Mask-Based Network for Self-Supervised Hyperspectral Change Detection》

T. Zhou et al., "STMNet: Single-Temporal Mask-Based Network for Self-Supervised Hyperspectral Change Detection," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-12, 2025, Art no. 5502712, doi: 10.1109/TGRS.2024.3523541. 

Introduction

This repository includes STMNet implementations in PyTorch version and partial datasets in the paper.

Requirements

Python 3.9
PyTorch 1.10.2

Citation

Please cite our paper if you use this code in your research.

T. Zhou et al., "STMNet: Single-Temporal Mask-Based Network for Self-Supervised Hyperspectral Change Detection," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-12, 2025, Art no. 5502712, doi: 10.1109/TGRS.2024.3523541.

@ARTICLE{10817647,
  author={Zhou, Tianyuan and Luo, Fulin and Fu, Chuan and Guo, Tan and Wang, Xiaopan and Du, Bo and Gao, Xinbo},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={STMNet: Single-Temporal Mask-Based Network for Self-Supervised Hyperspectral Change Detection}, 
  year={2025},
  volume={63},
  number={},
  pages={1-12},
  keywords={Feature extraction;Labeling;Training;Hyperspectral imaging;Image reconstruction;Vectors;Data mining;Accuracy;Telecommunications;Sensors;Change detection (CD);hyperspectral image (HSI);mask;multiscale feature;single temporal},
  doi={10.1109/TGRS.2024.3523541}}

License

Code and datasets are released for non-commercial and research purposes only. For commercial purposes, please contact the authors.