[CVPR 2025 Highlight ✨] Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation
This repository contains the source code of Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation.
Jun. 3th, 2025: The implementation code has been released.
- Ubuntu 20.04, with Python 3.8.0, PyTorch 1.12.0, CUDA 11.6, multi gpus(8) - Nvidia RTX 3090.
- You can install all dependencies with the provided requirements file.
pip install -r requirements.txtPASTIS dataset
The original PASTIS dataset is accessible here. We follow the TSViT to divide each sample into 24x24 patches by running the script:
python data/PASTIS24/data2windows.py --rootdir <...> --savedir <...> --HWout 24The reorganized directory should be:
PASTIS
├── pickle24x24
│ ├── 40562_9.pickle
│ └── ...
├── fold-paths
│ ├── fold_1_paths.csv
│ └── ...
In addition, we generate multi-class labels for each patch by running the following script:
python data/PASTIS24/seg2cls_label.py --pickle_path <...>/PASTIS/pickle24x24 Germany dataset
The original Germany dataset is accessible here, we can download the dataset (40GB) via:
wget https://zenodo.org/record/5712933/files/data_IJGI18.zipThe size of each sample in Germany dataset is 24x24, so we only need to generate the multi-class labels with the above script without splitting.
bash run.sh $workspace $dataset_pathPlease cite our work if you find it helpful to your research.
@inproceedings{zhu2025exact,
title={Exact: Exploring space-time perceptive clues for weakly supervised satellite image time series semantic segmentation},
author={Zhu, Hao and Zhu, Yan and Xiao, Jiayu and Xiao, Tianxiang and Ma, Yike and Zhang, Yucheng and Dai, Feng},
booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
pages={14036--14045},
year={2025}
}This repo is built upon TSViT and PASTIS, thanks for their excellent works!