Vision Transformers for Zero-shot Face Presentation Attack Detection

Description

The vulnerability of face recognition systems to presentation attacks has limited their application in security-critical scenarios. Automatic methods of detecting such malicious attempts are essential for the safe use of facial recognition technology. Although various methods have been suggested for detecting such attacks, most of them over-fit the training set and fail in generalizing to unseen attacks and environments.

We used transfer learning from the vision transformer model for the zero-shot presentation attack detection task.

Publications

George, A. and Marcel, S. (2021). On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing. International Joint Conference on Biometrics (IJCB 2021).

Links

• Repository: https://gitlab.idiap.ch/bob/bob.paper.ijcb2021_vision_transformer_pad

Advantages

The proposed approach outperforms the state-of-the-art methods in the zero-shot protocols in the HQ-WMCA and SiW-M datasets by a large margin. Besides, the model achieves a significant boost in cross-database performance as well.

Applications

• Face Recognition
• Security

Technology Readiness Level

TRL 5

---

Vision Transformer model adapted for the presentation attack detection (PAD) task. The final layer is replaced and finetuned for the binary classification task.

Contact us for more information

• Interested in using our technologies?
• Interested to know more about the licensing possibilities and conditions?

Contact us