Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing

doi:10.1016/j.patcog.2021.107888

	Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing
	Jia, Yunpei 1,2; Zhang, Jie 1,2; Shan, Shiguang 1,2,3; Chen, Xilin 1,2
	2021-07-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	115 页码:13
摘要	Due to the environmental differences, many face anti-spoofing methods fail to generalize to unseen scenarios. In light of this, we propose a unified unsupervised and semi-supervised domain adaptation network (USDAN) for cross-scenario face anti-spoofing, aiming at minimizing the distribution discrepancy between the source and the target domains. Specifically, two modules, i.e., marginal distribution alignment module (MDA) and conditional distribution alignment module (CDA), are designed to seek a domain-invariant feature space via adversarial learning and make the features of the same class compact, respectively. By adding/removing the CDA module, the network can be easily switched for semisupervised/unsupervised setting, in which sense our method is named with & ldquo;unified & rdquo;. Moreover, the adaptive cross-entropy loss and normalization techniques are further incorporated to improve the generalization. Extensive experimental results show that the proposed USDAN outperforms state-of-the-art methods on several public datasets. (c) 2021 Elsevier Ltd. All rights reserved.
关键词	Face anti-spoofing Face presentation attack detection Domain adaptation Deep learning
DOI	10.1016/j.patcog.2021.107888
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102402] ; Natural Science Foundation of China[61806188]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000639745600001
出版者	ELSEVIER SCI LTD
引用统计	被引频次：39[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/2XEOYT63/16681
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Chinese Acad Sci CAS, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Jia, Yunpei,Zhang, Jie,Shan, Shiguang,et al. Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing[J]. PATTERN RECOGNITION,2021,115:13.
APA	Jia, Yunpei,Zhang, Jie,Shan, Shiguang,&Chen, Xilin.(2021).Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing.PATTERN RECOGNITION,115,13.
MLA	Jia, Yunpei,et al."Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing".PATTERN RECOGNITION 115(2021):13.