/PP-SAM

Primary LanguagePythonBSD 3-Clause "New" or "Revised" LicenseBSD-3-Clause

PP-SAM

Official Pytorch implementation of the paper PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation published in CVPRW 2024.

Md Mostafijur Rahman1*, Mustafa Munir1, Debesh Jha2, Ulas Bagci2, Radu Marculescu1

1The University of Texas at Austin, 2Northwestern University, *Corresponding Author

Update

***We released the training code

Fine-tuning pipeline

Citations

@inproceedings{rahman2024pp,
  title={PP-SAM: Perturbed Prompts for Robust Adaption of Segment Anything Model for Polyp Segmentation},
  author={Rahman, Md Mostafijur and Munir, Mustafa and Jha, Debesh and Bagci, Ulas and Marculescu, Radu},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4989--4995},
  year={2024}
}