Meta-Teacher For Face Anti-Spoofing

doi:10.1109/TPAMI.2021.3091167

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

	Meta-Teacher For Face Anti-Spoofing
	Qin, Yunxiao 1,2; Yu, Zitong 3; Yan, Longbin 2; Wang, Zezheng 4; Zhao, Chenxu 5; Lei, Zhen6,7,8
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2022-10-01
卷号	44 期号:10 页码:6311-6326
通讯作者	Lei, Zhen(zlei@nlpr.ia.ac.cn)
摘要	Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs). Existing FAS methods usually supervise PA detectors with handcrafted binary or pixel-wise labels. However, handcrafted labels may are not the most adequate way to supervise PA detectors learning sufficient and intrinsic spoofing cues. Instead of using the handcrafted labels, we propose a novel Meta-Teacher FAS (MT-FAS) method to train a meta-teacher for supervising PA detectors more effectively. The meta-teacher is trained in a bi-level optimization manner to learn the ability to supervise the PA detectors learning rich spoofing cues. The bi-level optimization contains two key components: 1) a lower-level training in which the meta-teacher supervises the detector's learning process on the training set; and 2) a higher-level training in which the meta-teacher's teaching performance is optimized by minimizing the detector's validation loss. Our meta-teacher differs significantly from existing teacher-student models because the meta-teacher is explicitly trained for better teaching the detector (student), whereas existing teachers are trained for outstanding accuracy neglecting teaching ability. Extensive experiments on five FAS benchmarks show that with the proposed MT-FAS, the trained meta-teacher 1) provides better-suited supervision than both handcrafted labels and existing teacher-student models; and 2) significantly improves the performances of PA detectors.
关键词	Detectors Face recognition Training Faces Feature extraction Training data Optimization Face anti-spoofing meta-teacher pixel-wise supervision deep-learning
DOI	10.1109/TPAMI.2021.3091167
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020AAA0140002] ; National Natural Science Foundation of China[61876178] ; National Natural Science Foundation of China[61976229]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000853875300035
出版者	IEEE COMPUTER SOC
引用统计	被引频次：20[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50138
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	Lei, Zhen
作者单位	1.Commun Univ China, Neurosci & Intelligent Media Inst NIMI, Beijing 100024, Peoples R China 2.Northwestern Polytech Univ, Xian 710072, Peoples R China 3.Univ Oulu, Ctr Machine Vis & Signal Anal, Oulu 90014, Finland 4.Beijing Kwai Technol Co Ltd, Beijing 102600, Peoples R China 5.MiningLamp Technol, Beijing 100000, Peoples R China 6.Chinese Acad Sci CASIA, Ctr Biometr & Secur Res CBSR, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China 7.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, 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	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Qin, Yunxiao,Yu, Zitong,Yan, Longbin,et al. Meta-Teacher For Face Anti-Spoofing[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2022,44(10):6311-6326.
APA	Qin, Yunxiao,Yu, Zitong,Yan, Longbin,Wang, Zezheng,Zhao, Chenxu,&Lei, Zhen.(2022).Meta-Teacher For Face Anti-Spoofing.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,44(10),6311-6326.
MLA	Qin, Yunxiao,et al."Meta-Teacher For Face Anti-Spoofing".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44.10(2022):6311-6326.