Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing

doi:10.1109/TIFS.2023.3326370

CSpace

	Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing
	Long, Xingming 1,2; Zhang, Jie 1,2; Wu, Shuzhe 3; Jin, Xin ; Shan, Shiguang 1,2
	2024
发表期刊	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
ISSN	1556-6013
卷号	19 页码:851-862
摘要	Improving generalization to unseen scenarios is one of the greatest challenges in Face Anti-spoofing (FAS). Most previous FAS works focus on domain debiasing to eliminate the distribution discrepancy between training and test data. However, a crucial but usually neglected bias factor is the face identity. Generally, the identity distribution varies across the FAS datasets as the participants in these datasets are from different regions, which will lead to serious identity bias in the cross-dataset FAS tasks. In this work, we resort to causal learning and propose Dual Sampling based Causal Intervention (DSCI) for face anti-spoofing, which improves the generalization of the FAS model by eliminating the identity bias. DSCI treats the bias as a confounder and applies the backdoor adjustment through the proposed dual sampling on the face identity and the FAS feature. Specifically, we first sample the data uniformly on the identity distribution that is obtained by a pretrained face recognition model. By feeding the sampled data into a network, we can get an estimated FAS feature distribution and sample the FAS feature on it. Sampling the FAS feature from a complete estimated distribution can include potential counterfactual features in the training, which effectively expands the training data. The dual sampling process helps the model learn the real causality between the FAS feature and the input liveness, allowing the model to perform more stably across various identity distributions. Extensive experiments demonstrate our proposed method outperforms the state-of-the-art methods on both intra- and cross-dataset evaluations.
关键词	Causal intervention backdoor adjustment face anti-spoofing out-of-distribution
DOI	10.1109/TIFS.2023.3326370
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001119528500017
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38797
专题	中国科学院计算技术研究所
通讯作者	Shan, Shiguang
作者单位	1.Chinese Acad Sci, Inst Comp Technol ICT, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Beijing Huawei Cloud Comp Technol Co Ltd, Beijing 100095, Peoples R China
推荐引用方式 GB/T 7714	Long, Xingming,Zhang, Jie,Wu, Shuzhe,et al. Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2024,19:851-862.
APA	Long, Xingming,Zhang, Jie,Wu, Shuzhe,Jin, Xin,&Shan, Shiguang.(2024).Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,19,851-862.
MLA	Long, Xingming,et al."Dual Sampling Based Causal Intervention for Face Anti-Spoofing With Identity Debiasing".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19(2024):851-862.