- [✔️] Update codebase for KuroSiwo v2 + updated mean/stds
- [✔️] Updated citation 
- [ ] TODO: Expand README with more elaborate guidelines
- [ ] TODO: Upload Kuro-Siwo to HuggingFace

• Download the dataset
• Data preprocessing
• Repository structure
• Pretrained models
• Citation

• The Kuro Siwo GRD Dataset can be downloaded either:

  • from the following link,

  • or by executing scripts/download_kuro_siwo.sh. This script will download and prepare the Kuro Siwo GRDD dataset for deep learning.

    Usage

    1. Make sure to grant the necessary rights by executing chmod +x scripts/download_kuro_siwo.sh
    2. Execute scripts/download_kuro_siwo.sh DESIRED_DATASET_ROOT_PATH e.g: ./download_kuro_siwo.sh KuroRoot

• The SLC Preprocessed products can be downloaded from the following link.

• Similarly, the cropped SLC patches (224x224 pixels) can be acquired from the following link.

The preprocessing pipelines used to generate the GRD and SLC products can be found at configs/grd_preprocessing.xml and configs/slc_preprocessing.xml repsectively.

• Kuro Siwo uses the black python formatter. To activate it install pre-commit, running pip install pre-commit and execute pre-commit install.
• Training starts by running python main.py. The configurations are defined in the configs directory e.g
  • model,
  • training pipeline
    • Segmentation,
    • change detection
  • hyperparameters
• main.py supports command line arguments that override the config files. e.g

     python main.py --method=unet --backbone=resnet18 --dem=True --slope=False --batch_size=32
  

The weights of the top performing models can be accessed using the following links:

• FloodViT
• SNUNet

If you use this work please cite:

@inproceedings{NEURIPS2024_43612b06,
 author = {Bountos, Nikolaos Ioannis and Sdraka, Maria and Zavras, Angelos and Karavias, Andreas and Karasante, Ilektra and Herekakis, Themistocles and Thanasou, Angeliki and Michail, Dimitrios and Papoutsis, Ioannis},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
 pages = {38105--38121},
 publisher = {Curran Associates, Inc.},
 title = {Kuro Siwo: 33 billion m\^{}2 under the water. A global multi-temporal satellite dataset for rapid flood mapping},
 url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/43612b0662cb6a4986edf859fd6ebafe-Paper-Datasets_and_Benchmarks_Track.pdf},
 volume = {37},
 year = {2024}
}