Code repository for our paper titled "Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-World Applications" (CVPRW Oral).

• Another work, Medical SAM Adapter which addresses the issue of lacking domain-specific medical knowledge in the SAM, are available now.
• Long version of this work has been accepted by Machine Intelligence Research.
• This work is awarded as Best Paper (Most Insightful Paper) at the CVPR'23 VISION Workshop.
• Evaluation code has been released.
• This work has been accepted as an Oral Presentation at the CVPR'23 VISION Workshop.

1. Download the vit_b, vit_h and vim_l model from https://github.com/facebookresearch/segment-anything then put these models to the model_ck folder.
2. Prepared own datasets put into the datasets folder.
3. Set right path in /scripts/amg.py, then:

run amg.py

1. After inferring, the SAM model generates predicted maps from a singer RGB image (multimask_output=True). Check right path in sam_dice_f1_mae.py or sam_f1_dice_mae.py to decide the best map selected by Dice or F1 metrics.

1. Prepared these methods predicted maps to put into the other_methods_output folder.
2. Check right path in /scripts/other_methods_dice_mae.py, then:

run other_methods_dice_mae.py

The download links of the dataset involved in our work are provided below.

If you find our work useful for your research or applications, please cite using this BibTeX:

@article{Jisam2024,
      author={Ji, Wei and Li, Jingjing and Bi, Qi and Liu, Tingwei and Li, Wenbo and Cheng, Li},
      journal={Machine Intelligence Research},
      title={Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications},
      year={2024},
      volume={21},
      pages={617--630},
      publisher={Springer}
}
@misc{wu2023medical,
      title={Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation}, 
      author={Junde Wu and Wei Ji and Yuanpei Liu and Huazhu Fu and Min Xu and Yanwu Xu and Yueming Jin},
      year={2023},
      eprint={2304.12620},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Thanks for the efforts of the authors involved in the Segment Anything.