Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing

TL;DR

This paper introduces a face anti-spoofing method using Vision Transformer intermediate features, combined with novel data augmentation techniques, achieving improved detection accuracy on standard datasets.

Contribution

It leverages intermediate features of Vision Transformer for face anti-spoofing and proposes two new data augmentation methods to enhance detection performance.

Findings

Effective detection of spoofing attacks demonstrated on OULU-NPU and SiW datasets.

Intermediate ViT features provide a good balance of local and global information.

Data augmentation methods improve overall detection accuracy.

Abstract

Face recognition systems are designed to be robust against changes in head pose, illumination, and blurring during image capture. If a malicious person presents a face photo of the registered user, they may bypass the authentication process illegally. Such spoofing attacks need to be detected before face recognition. In this paper, we propose a spoofing attack detection method based on Vision Transformer (ViT) to detect minute differences between live and spoofed face images. The proposed method utilizes the intermediate features of ViT, which have a good balance between local and global features that are important for spoofing attack detection, for calculating loss in training and score in inference. The proposed method also introduces two data augmentation methods: face anti-spoofing data augmentation and patch-wise data augmentation, to improve the accuracy of spoofing attack detection. We demonstrate the effectiveness of the proposed method through experiments using the OULU-NPU and SiW datasets. The project page is available at: https://gsisaoki.github.io/FAS-ViT-CVPRW/ .