Citation

If you use RankSEG in your research, please consider citing our work. We appreciate your support! ⭐

Papers

RankSEG is based on the following research papers:

Foundational Paper (JMLR 2023)

The core RankSEG framework and methodology:

@article{rankseg2023,
   title={RankSEG: A Consistent Ranking-based Framework for Segmentation},
   author={Dai, Ben and Li, Chunlin},
   journal={Journal of Machine Learning Research},
   volume={24},
   number={224},
   pages={1--50},
   year={2023}
}

Paper Link: https://www.jmlr.org/papers/v24/22-0712.html

Extended Work (NeurIPS 2025)

The RMA solver for efficient segmentation:

@inproceedings{rankseg2025,
   title={RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation},
   author={Wang, Zixun and Dai, Ben},
   booktitle={Advances in Neural Information Processing Systems},
   year={2025}
}

Paper Link: https://openreview.net/forum?id=4tRMm1JJhw

License

RankSEG is released under the BSD 3-Clause License. See the LICENSE file for details.