CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing

doi:10.1007/s11263-024-02132-5

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing
	Liu, Xing 2; Su, Anyang 1,4; Wu, Minghui 1; Yu, Zitong 3; Wu, Kangle 4; An, Da 4; Hao, Jie1 ; Xu, Mengzhen 5; Zhao, Chenxu 1,4; Lei, Zhen6,7,8
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN	0920-5691
	2024-06-10
页码	16
通讯作者	Zhao, Chenxu(zhaochenxu@mininglamp.com) ; Lei, Zhen(zlei@nlpr.ia.ac.cn)
摘要	Face Anti-Spoofing (FAS) is essential to secure face recognition systems from various physical attacks. A sufficient and diverse training set helps to build robust FAS models. To exploit the potential of FAS datasets, we propose to generate high-quality data including live and diverse presentation attacks (PAs) faces, for data augmentation during the model training stage. Our method is called Cross-label Generative augmentation for Face Anti-Spoofing (CG-FAS), which could convert a live face into a 3D high-fidelity mask, replay, print, or other extra physical PAs. Correspondingly, CG-FAS can also restore a specific physical presentation attack into a live face. This function is realized by innovatively building an Interchange Bridge matrix, which stores disentangled spoof clues between PAs and live faces. To verify the effects of these generated data, we utilize them as augmentation data and conduct experiments on several typical FAS benchmarks. Extensive experimental results demonstrate the superior performance gain with CG-FAS for off-the-shelf data-driven FAS models. We hope the CG-FAS can shine a light on the deep FAS community to alleviate the data-hungry issue. The code will be released soon at: https://github.com/liuxingwt/CG-FAS.
关键词	Face Anti-Spoofing Data augmentation Generative model Face editing
DOI	10.1007/s11263-024-02132-5
收录类别	SCI
语种	英语
资助项目	Brain-like General Vision Model and Applications project[2022ZD0160402] ; Chinese National Natural Science Foundation[62276254] ; Chinese National Natural Science Foundation[U23B2054] ; Frontier Interdiscipline Project of Tsinghua University[20221080082] ; National Natural Science Foundation of China[62306061] ; Guangdong Basic and Applied Basic Research Foundation[2023A1515140037]
项目资助者	Brain-like General Vision Model and Applications project ; Chinese National Natural Science Foundation ; Frontier Interdiscipline Project of Tsinghua University ; National Natural Science Foundation of China ; Guangdong Basic and Applied Basic Research Foundation
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001242698400001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58668
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Zhao, Chenxu; Lei, Zhen
作者单位	1.Mininglamp Technol, Beijing, Peoples R China 2.Zelos Technol, Beijing, Peoples R China 3.Great Bay Univ, Dongguan, Peoples R China 4.Shanghai Artificial Intelligence Lab, Shanghai, Peoples R China 5.Tsinghua Univ, Dept Hydraul Engn, Beijing, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 7.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 8.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, Hong Kong Inst Sci & Innovat, Hong Kong, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Liu, Xing,Su, Anyang,Wu, Minghui,et al. CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:16.
APA	Liu, Xing.,Su, Anyang.,Wu, Minghui.,Yu, Zitong.,Wu, Kangle.,...&Lei, Zhen.(2024).CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing.INTERNATIONAL JOURNAL OF COMPUTER VISION,16.
MLA	Liu, Xing,et al."CG-FAS: Cross-label Generative Augmentation for Face Anti-Spoofing".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):16.