association-rosia / flair-2

Engage in a semantic segmentation challenge for land cover description using multimodal remote sensing earth observation data, delving into real-world scenarios with a dataset comprising 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions.

Home Page:https://codalab.lisn.upsaclay.fr/competitions/13447

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

๐Ÿ›ฐ๏ธ FLAIR #2

The challenge involves a semantic segmentation task focusing on land cover description using multimodal remote sensing earth observation data. Participants will explore heterogeneous data fusion methods in a real-world scenario. Upon registration, access is granted to a dataset containing 70,000+ aerial imagery patches with pixel-based annotations and 50,000 Sentinel-2 satellite acquisitions.

This project was made possible by our compute partners 2CRSi and NVIDIA.

๐Ÿ† Challenge ranking

The score of the challenge was the mIoU.
Our solution was the 8th one (out of 30 teams) with a mIoU equal to 0.62610 ๐ŸŽ‰.

The podium:
๐Ÿฅ‡ strakajk - 0.64130
๐Ÿฅˆ Breizhchess - 0.63550
๐Ÿฅ‰ qwerty64 - 0.63510

๐Ÿ–ผ๏ธ Result example

Aerial input image Multi-class label Multi-class pred

View more results on the WandB project.

๐Ÿ›๏ธ Model architecture

#๏ธโƒฃ Command lines

Launch a training

python src/models/train_model.py <hyperparams args>

Create a submission

python src/models/predict_model.py -n {model.ckpt}

๐Ÿ”ฌ References

Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.

Garioud, A., De Wit, A., Poupรฉe, M., Valette, M., Giordano, S., & Wattrelos, B. (2023). FLAIR# 2: textural and temporal information for semantic segmentation from multi-source optical imagery. arXiv preprint arXiv:2305.14467.

Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, 12077-12090.

๐Ÿ“ Citing

@misc{RebergaUrgell:2023,
  Author = {Louis Reberga and Baptiste Urgell},
  Title = {FLAIR #2},
  Year = {2023},
  Publisher = {GitHub},
  Journal = {GitHub repository},
  Howpublished = {\url{https://github.com/association-rosia/flair-2}}
}

๐Ÿ›ก๏ธ License

Project is distributed under MIT License

๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป Contributors

Louis REBERGA

Baptiste URGELL

About

Engage in a semantic segmentation challenge for land cover description using multimodal remote sensing earth observation data, delving into real-world scenarios with a dataset comprising 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions.

https://codalab.lisn.upsaclay.fr/competitions/13447

License:MIT License


Languages

Language:Jupyter Notebook 99.8%Language:Python 0.2%