S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Rizhao, Yu, Zitong, Kong, Chenqi, Li, Haoliang, Chen, Changsheng, Hu, Yongjian, Kot, Alex
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911925417279488
author Cai, Rizhao
Yu, Zitong
Kong, Chenqi
Li, Haoliang
Chen, Changsheng
Hu, Yongjian
Kot, Alex
author_facet Cai, Rizhao
Yu, Zitong
Kong, Chenqi
Li, Haoliang
Chen, Changsheng
Hu, Yongjian
Kot, Alex
contents Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition system by presenting spoofed faces. State-of-the-art FAS techniques predominantly rely on deep learning models but their cross-domain generalization capabilities are often hindered by the domain shift problem, which arises due to different distributions between training and testing data. In this study, we develop a generalized FAS method under the Efficient Parameter Transfer Learning (EPTL) paradigm, where we adapt the pre-trained Vision Transformer models for the FAS task. During training, the adapter modules are inserted into the pre-trained ViT model, and the adapters are updated while other pre-trained parameters remain fixed. We find the limitations of previous vanilla adapters in that they are based on linear layers, which lack a spoofing-aware inductive bias and thus restrict the cross-domain generalization. To address this limitation and achieve cross-domain generalized FAS, we propose a novel Statistical Adapter (S-Adapter) that gathers local discriminative and statistical information from localized token histograms. To further improve the generalization of the statistical tokens, we propose a novel Token Style Regularization (TSR), which aims to reduce domain style variance by regularizing Gram matrices extracted from tokens across different domains. Our experimental results demonstrate that our proposed S-Adapter and TSR provide significant benefits in both zero-shot and few-shot cross-domain testing, outperforming state-of-the-art methods on several benchmark tests. We will release the source code upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04038
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
Cai, Rizhao
Yu, Zitong
Kong, Chenqi
Li, Haoliang
Chen, Changsheng
Hu, Yongjian
Kot, Alex
Computer Vision and Pattern Recognition
Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition system by presenting spoofed faces. State-of-the-art FAS techniques predominantly rely on deep learning models but their cross-domain generalization capabilities are often hindered by the domain shift problem, which arises due to different distributions between training and testing data. In this study, we develop a generalized FAS method under the Efficient Parameter Transfer Learning (EPTL) paradigm, where we adapt the pre-trained Vision Transformer models for the FAS task. During training, the adapter modules are inserted into the pre-trained ViT model, and the adapters are updated while other pre-trained parameters remain fixed. We find the limitations of previous vanilla adapters in that they are based on linear layers, which lack a spoofing-aware inductive bias and thus restrict the cross-domain generalization. To address this limitation and achieve cross-domain generalized FAS, we propose a novel Statistical Adapter (S-Adapter) that gathers local discriminative and statistical information from localized token histograms. To further improve the generalization of the statistical tokens, we propose a novel Token Style Regularization (TSR), which aims to reduce domain style variance by regularizing Gram matrices extracted from tokens across different domains. Our experimental results demonstrate that our proposed S-Adapter and TSR provide significant benefits in both zero-shot and few-shot cross-domain testing, outperforming state-of-the-art methods on several benchmark tests. We will release the source code upon acceptance.
title S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.04038