Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Mika, Ito, Koichi, Aoki, Takafumi, Ohki, Tetsushi, Nishigaki, Masakatsu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913894976454656
author Feng, Mika
Ito, Koichi
Aoki, Takafumi
Ohki, Tetsushi
Nishigaki, Masakatsu
author_facet Feng, Mika
Ito, Koichi
Aoki, Takafumi
Ohki, Tetsushi
Nishigaki, Masakatsu
contents 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/ .
format Preprint
id arxiv_https___arxiv_org_abs_2505_24402
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing
Feng, Mika
Ito, Koichi
Aoki, Takafumi
Ohki, Tetsushi
Nishigaki, Masakatsu
Computer Vision and Pattern Recognition
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/ .
title Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.24402