On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing

This package contains source code to replicate the experimental results published in the following paper:

@inproceedings{georgeijcb2021,
    author = {Anjith George and Sebastien Marcel},
    title = {On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing},
    year = {2021},
    booktitle = {International Joint Conference on Biometrics (IJCB 2021)},
}

If you use this package and/or its results, please consider citing the paper.

The main idea in the paper is the use of vision-transformers for face-anti-spoofing task.

Fig. 1 Diagram of the proposed framework.

User guide

• Training ViT Model for PAD
  • Preprocessing data
  • Training the CNN Model with ViT
  • Running experiments with the trained model
  • Evaluating results
• Using pretrained models
• References