Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection

doi:10.1109/TIFS.2020.3002390

	Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection
	Wang, Guoqing 1,2; Han, Hu 1,3; Shan, Shiguang 1,2,4; Chen, Xilin 1,2
	2021
发表期刊	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
ISSN	1556-6013
卷号	16 页码:56-69
摘要	Face presentation attack detection (PAD) is essential for securing the widely used face recognition systems. Most of the existing PAD methods do not generalize well to unseen scenarios because labeled training data of the new domain is usually not available. In light of this, we propose an unsupervised domain adaptation with disentangled representation (DR-UDA) approach to improve the generalization capability of PAD into new scenarios. DR-UDA consists of three modules, i.e., ML-Net, UDA-Net and DR-Net. ML-Net aims to learn a discriminative feature representation using the labeled source domain face images via metric learning. UDA-Net performs unsupervised adversarial domain adaptation in order to optimize the source domain and target domain encoders jointly, and obtain a common feature space shared by both domains. As a result, the source domain PAD model can be effectively transferred to the unlabeled target domain for PAD. DR-Net further disentangles the features irrelevant to specific domains by reconstructing the source and target domain face images from the common feature space. Therefore, DR-UDA can learn a disentangled representation space which is generative for face images in both domains and discriminative for live vs. spoof classification. The proposed approach shows promising generalization capability in several public-domain face PAD databases.
关键词	Face Feature extraction Testing Adaptation models Databases Deep learning Three-dimensional displays Face presentation attack detection face liveness detection face anti-spoofing adversarial domain adaptation metric learning disentangled representation
DOI	10.1109/TIFS.2020.3002390
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0700804] ; Natural Science Foundation of China[61672496]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000554454600005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：65[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/15849
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Han, Hu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China 4.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Wang, Guoqing,Han, Hu,Shan, Shiguang,et al. Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021,16:56-69.
APA	Wang, Guoqing,Han, Hu,Shan, Shiguang,&Chen, Xilin.(2021).Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16,56-69.
MLA	Wang, Guoqing,et al."Unsupervised Adversarial Domain Adaptation for Cross-Domain Face Presentation Attack Detection".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16(2021):56-69.