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

TL;DR

This paper demonstrates that transfer learning with vision transformers significantly improves zero-shot face anti-spoofing, outperforming existing methods in generalization to unseen attacks and environments.

Contribution

The study introduces a vision transformer-based transfer learning approach for zero-shot face anti-spoofing, showing superior generalization over state-of-the-art methods.

Findings

Outperforms state-of-the-art in zero-shot protocols on HQ-WMCA and SiW-M datasets.

Achieves significant improvements in cross-database performance.

Demonstrates robustness to unseen attacks and environments.

Abstract

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. In this work, we use transfer learning from the vision transformer model for the zero-shot anti-spoofing task. The effectiveness of the proposed approach is demonstrated through experiments in publicly available datasets. 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.