Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization

Environment

You can install all the requirements via:

pip install -r requirements.txt

Our code is based on the SAM-Adapter-PyTorch repository.

Data sources:

• FaceForensics
• Detect and Locate

To run our code, you can use the following command:

bash run.sh

Please consider citing the following paper if you find it interesting or helpful to your research

@article{lai2023detect,
  title={Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization},
  author={Lai, Yingxin and Luo, Zhiming and Yu, Zitong},
  journal={Chinese Conference on Biometric Recognition，CCBR},
  year={2023}
}