Deep Learning for Face Anti-Spoofing: A Survey

Yu, Zitong; Qin, Yunxiao; Li, Xiaobai; Zhao, Chenxu; Lei, Zhen; Zhao, Guoying

doi:10.48550/arxiv.2106.14948

Cited by 19 publications

(19 citation statements)

References 205 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two related works [34,64] using ViT for rPPG feature representation. TransRPPG [64] extracts rPPG features from the preprocessed signal maps via ViT for face 3D mask presentation attack detection [68]. Based on the temporal shift networks [30,33], EfficientPhys-T [34] adds several swim transformer [37] layers for global spatial attention.…”

Section: Related Workmentioning

confidence: 99%

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

Yu¹,

Shen²,

Shi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e.g., remote healthcare and affective computing). Recent deep learning approaches focus on mining subtle rPPG clues using convolutional neural networks with limited spatio-temporal receptive fields, which neglect the long-range spatio-temporal perception and interaction for rPPG modeling. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture, to adaptively aggregate both local and global spatio-temporal features for rPPG representation enhancement. As key modules in PhysFormer, the temporal difference transformers first enhance the quasi-periodic rPPG features with temporal difference guided global attention, and then refine the local spatio-temporal representation against interference. Furthermore, we also propose the label distribution learning and a curriculum learning inspired dynamic constraint in frequency domain, which provide elaborate supervisions for PhysFormer and alleviate overfitting. Comprehensive experiments are performed on four benchmark datasets to show our superior performance on both intra-and cross-dataset testings. One highlight is that, unlike most transformer networks needed pretraining from large-scale datasets, the proposed PhysFormer can be easily trained from scratch on rPPG datasets, which makes it promising as a novel transformer baseline for the rPPG community. The codes will be released at https://github.com/ZitongYu/PhysFormer.

show abstract

Section: Related Workmentioning

confidence: 99%

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

Yu¹,

Shen²,

Shi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent literature surveys (e.g., [51,82]) have concluded that both handcrafted and deep features yield in satisfying classification performance in identifying known PAIs but often fail to detect unknown PAIs and more sophisticated facial artefacts, thus continuous efforts are necessary to update face anti-spoofing algorithms to detect rapidly evolving PAs. Although earlier the CVPR2020 cross-ethnicity face PAD challenge considered also a cross-PAI setting (i.e., training on the video-replay attacks and testing on the print and mask PAIs), the types and quality of the unknown PAIs were still limited from the generalized PAD point of view.…”

Section: Livdet-face 2021 -Face Liveness Detection Competition (Ijcb2...mentioning

confidence: 99%

“…Despite the recent progress in deep learning based face anti-spoofing methods [51,82] with powerful representation capacity, it is difficult to tell what are the best or most promising feature learning approaches for generalized face PAD. Along with the development in manufacturing technologies, it has become even cheaper for an attacker to exploit a known vulnerability of a face authentication system with different kinds of facial artefacts, such as a realistic 3D mask made of plaster.…”

Section: Introductionmentioning

confidence: 99%

Review of Face Presentation Attack Detection Competitions

Yu¹,

Komulainen²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Face presentation attack detection (PAD) has received increasing attention ever since the vulnerabilities to spoofing have been widely recognized. The state of the art in unimodal and multi-modal face anti-spoofing has been assessed in eight international competitions organized in conjunction with major biometrics and computer vision conferences in 2011, 2013, 2017, 2019, 2020 and 2021, each introducing new challenges to the research community. In this chapter, we present the design and results of the five latest competitions from 2019 until 2021. The first two challenges aimed to evaluate the effectiveness of face PAD in multi-modal setup introducing near-infrared (NIR) and depth modalities in addition to colour camera data, while the latest three competitions focused on evaluating domain and attack type generalization abilities of face PAD algorithms operating on conventional colour images and videos. We also discuss the lessons learnt from the competitions and future challenges in the field in general.

show abstract

“…Among various techniques that aim to mitigate the domain shift problem and improve generalization performance, one promising research direction is to combine task-aware handcrafted features and deep neural networks, and such methods are summarized as hybrid methods [20]. As illustrated in the top diagram of Fig.…”

Section: Introductionmentioning

confidence: 99%

Learning Meta Pattern for Face Anti-Spoofing

Cai,

Li,

Wan

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep Learning for Face Anti-Spoofing: A Survey

Cited by 19 publications

References 205 publications

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

Review of Face Presentation Attack Detection Competitions

Learning Meta Pattern for Face Anti-Spoofing

Contact Info

Product

Resources

About