Face Anti-Spoofing with Human Material Perception

Yu, Zitong; Li, Xiaobai; Niu, Xuesong; Shi, Jingang; Zhao, Guoying

doi:10.48550/arxiv.2007.02157

Cited by 5 publications

(8 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most works [7], [19], [47], [48] treat FAS as a binary classification supervised by simple binary cross-entropy loss. In contrast, pseudo depth labels [6], [9], reflection maps [5], [49], and binary mask label [19] are utilized as auxiliary supervision signals as the pixel-wise guidance is able to learn more detailed information. On the other hand, according to the dynamic discrepancy [13], [14] between live and spoofing faces, several video level methods are presented to exploit the dynamic spatio-temporal [8], [13], [50], [51] or rPPG [6], [52], [53] features for PAD.…”

Section: Related Workmentioning

confidence: 99%

“…In the past few years, both traditional [1], [2], [3] and deep learning-based [4], [5], [6], [7], [8], [9], [10] methods have shown effectiveness for presentation attack detection (PAD). On one hand, some classical local descriptors (e.g., local binary pattern (LBP) [11] and histogram of gradient (HOG) [2]) are robust for describing the detailed invariant information (e.g., color texture, moiré pattern and noise artifacts) from spoofing faces.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

157

102

View full text Add to dashboard Cite

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Existing methods heavily rely on the expert-designed networks, which may lead to a sub-optimal solution for FAS task. Here we propose the first FAS method based on neural architecture search (NAS), called NAS-FAS, to discover the well-suited task-aware networks. Unlike previous NAS works mainly focus on developing efficient search strategies in generic object classification, we pay more attention to study the search spaces for FAS task. The challenges of utilizing NAS for FAS are in two folds: the networks searched on 1) a specific acquisition condition might perform poorly in unseen conditions, and 2) particular spoofing attacks might generalize badly for unseen attacks. To overcome these two issues, we develop a novel search space consisting of central difference convolution and pooling operators. Moreover, an efficient static-dynamic representation is exploited for fully mining the FAS-aware spatio-temporal discrepancy. Besides, we propose Domain/Type-aware Meta-NAS, which leverages cross-domain/type knowledge for robust searching. Finally, in order to evaluate the NAS transferability for cross datasets and unknown attack types, we release a large-scale 3D mask dataset, namely CASIA-SURF 3DMask, for supporting the new 'cross-dataset cross-type' testing protocol. Experiments demonstrate that the proposed NAS-FAS achieves state-of-the-art performance on nine FAS benchmark datasets with four testing protocols.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Wan

Qin

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

157

102

View full text Add to dashboard Cite

show abstract

“…Based on auxiliary information, some methods regularized features from the perspective of disentanglement [30,15]. Some methods put forward specific convolution operators to extract spoof cues, such as CDCN [28], BCN [25], DC-CDN [27], etc. To achieve improvements in cross-testing, [21,5,20,12] adopted the strategy of domain generalization, meta-learning and few-shot learning.…”

Section: Related Workmentioning

confidence: 99%

Structure Destruction and Content Combination for Face Anti-Spoofing

Zhang¹,

Yao²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

In pursuit of consolidating the face verification systems, prior face anti-spoofing studies excavate the hidden cues in original images to discriminate real person and diverse attack types with the assistance of auxiliary supervision. However, limited by the following two inherent disturbances in their training process: 1) Complete facial structure in a single image. 2) Implicit subdomains in the whole dataset, these methods are prone to stick on memorization of the entire training dataset and show sensitivity to nonhomologous domain distribution. In this paper, we propose Structure Destruction Module and Content Combination Module to address these two limitations separately. The former mechanism destroys images into patches to construct a non-structural input, while the latter mechanism recombines patches from different subdomains or classes into a mixup construct. Based on this splitting-and-splicing operation, Local Relation Modeling Module is further proposed to model the second-order relationship between patches. We evaluate our method on extensive public datasets and promising experimental results to demonstrate the reliability of our method against the state-of-the-art competitors.

show abstract

“…Based on auxiliary information, the method [23,48] regularized features from the perspective of disentanglement. Some methods [43,44] put forward specific convolution operators to extract spoof cues, such as CDCN [45], BCN [40]. The above methods got high performance under the intra-dataset setting, where the testing data comes from a similar distribution of training data.…”

Section: Related Work 21 Face Anti-spoofingmentioning

confidence: 99%

Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing

Liu

Zhang

Yao

et al. 2021

Preprint

View full text Add to dashboard Cite

With various face presentation attacks arising under unseen scenarios, face anti-spoofing (FAS) based on domain generalization (DG) has drawn growing attention due to its robustness. Most existing methods utilize DG frameworks to align the features to seek a compact and generalized feature space. However, little attention has been paid to the feature extraction process for the FAS task, especially the influence of normalization, which also has a great impact on the generalization of the learned representation. To address this issue, we propose a novel perspective of face anti-spoofing that focuses on the normalization selection in the feature extraction process. Concretely, an Adaptive Normalized Representation Learning (ANRL) framework is devised, which adaptively selects feature normalization methods according to the inputs, aiming to learn domain-agnostic and discriminative representation. Moreover, to facilitate the representation learning, Dual Calibration Constraints are designed, including Inter-Domain Compatible loss and Inter-Class Separable loss, which provide a better optimization direction for generalizable representation. Extensive experiments and visualizations are presented to demonstrate the effectiveness of our method against the SOTA competitors. CCS CONCEPTS• Computing methodologies → Computer vision.

show abstract

Face Anti-Spoofing with Human Material Perception

Cited by 5 publications

References 64 publications

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing

Structure Destruction and Content Combination for Face Anti-Spoofing

Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing

Contact Info

Product

Resources

About