Polyp-SAM++

The official PyTorch code for the project Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?.

Polyp-SAM++ is the first text-guided polyp-segmentation method using segment anything model(SAM).

Polyp-SAM++ Results

Run in Colab

Open the Poly-SAM++.ipynb file in Google Colab and play with it!

Dataset -

• KVASIR-SEG: Link
• CVC-300: Link
• CVC-ClinicDB: Link

Additional Resources -

1. Segment Anything Model (SAM) for Medical Image Segmentation.
2. Awesome-Polyp-Segmentation

Citation -

@misc{biswas2023polypsam,
      title={Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?}, 
      author={Risab Biswas},
      year={2023},
      eprint={2308.06623},
      archivePrefix={arXiv},
      primaryClass={eess.IV}
}

Acknowledgment -

The author would like to extend a heartfelt appreciation to Luca Medeiros, the author, and creator of the repository langsegment-anything available at (https://github.com/luca-medeiros/lang-segment-anything). The remarkable work done by the author has been instrumental in making our project possible and has greatly contributed to its success.

Contact

If you have any question, please feel free to reach out to Risab Biswas.

Conclusion

We really appreciate your interest in my research. Thank you!