On Disentangling Spoof Trace for Generic Face Anti-spoofing

Liu, Yaojie; Stehouwer, Joel; Liu, Xiaoming

doi:10.1007/978-3-030-58523-5_24

Cited by 110 publications

(58 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised by Binary Mask: Compared with pseudo depth map, binary mask label [26], [27], [47], [48], [49], [50], [51] is easier to be generated and more generalizable to all PAs. To be specific, the binary supervision would be provided for the deep embedding features in each spatial position (second column in Fig.…”

Section: Review Of Pixel-wise Supervisionmentioning

confidence: 99%

“…Yu et al [48] searched lightweight FAS architectures with pixel-wise binary supervision. Liu et al [50] utilized Early Spoof Regressor with pixel-wise binary supervision to enhance discriminativeness of the generator. Ma et al [49] proposed a multi-regional CNN with the local binary classification loss to local patches.…”

Section: Review Of Pixel-wise Supervisionmentioning

confidence: 99%

“…Compared with binary scalar label, binary mask label [26], [27], [47], [48], [49], [50], [51] contains rich spatial context, which benefits the models' cognition about the position of spoofing attacks. In order to exploit multi-scale spatial information from binary mask label, we propose the concept of pyramid supervision, which decomposes the original pixel-wise label into multiple spatial scales for supervising multi-scale features.…”

Section: A Pyramid Binary Mask Supervisionmentioning

confidence: 99%

See 2 more Smart Citations

Revisiting Pixel-Wise Supervision for Face Anti-Spoofing

Shi

et al. 2021

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from the presentation attacks (PAs). As more and more realistic PAs with novel types spring up, it is necessary to develop robust algorithms for detecting unknown attacks even in unseen scenarios. However, deep models supervised by traditional binary loss (e.g., '0' for bonafide vs. '1' for PAs) are weak in describing intrinsic and discriminative spoofing patterns. Recently, pixel-wise supervision has been proposed for the FAS task, intending to provide more fine-grained pixel/patchlevel cues. In this paper, we firstly give a comprehensive review and analysis about the existing pixel-wise supervision methods for FAS. Then we propose a novel pyramid supervision, which guides deep models to learn both local details and global semantics from multi-scale spatial context. Extensive experiments are performed on five FAS benchmark datasets to show that, without bells and whistles, the proposed pyramid supervision could not only improve the performance beyond existing pixel-wise supervision frameworks, but also enhance the model's interpretability (i.e., locating the patch-level positions of PAs more reasonably). Furthermore, elaborate studies are conducted for exploring the efficacy of different architecture configurations with two kinds of pixel-wise supervisions (binary mask and depth map supervisions), which provides inspirable insights for future architecture/supervision design.

show abstract

Section: Review Of Pixel-wise Supervisionmentioning

confidence: 99%

Section: Review Of Pixel-wise Supervisionmentioning

confidence: 99%

Section: A Pyramid Binary Mask Supervisionmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting Pixel-Wise Supervision for Face Anti-Spoofing

Shi

et al. 2021

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…In the line of thought of going beyond the binary supervision by using only the labels of the two classes, another work used a depth map and the rPPG signal as the auxiliary supervision to improve the performance of the face anti-spoofing method [34]. More recently, the interpretability and explainability of machine learning models have gained relevance and more works are focused on the application of their methodologies in the field of biometrics and, in particular, to the face PAD problem whether by attempting to estimate the depth map [35][36][37], provide saliency maps in the CNN model [38,39] or even studies on the estimation of patterns that characterise an attack sample [38,40]. To the extent of the authors' knowledge, it is still a territory that has been explored very little to apply interpretability tools and analyse biometric recognition and PAD techniques from the xAI perspective.…”

Section: Xai For Biometrics and Padmentioning

confidence: 99%

An exploratory study of interpretability for face presentation attack detection

et al. 2021

View full text Add to dashboard Cite

Biometric recognition and presentation attack detection (PAD) methods strongly rely on deep learning algorithms. Though often more accurate, these models operate as complex black boxes. Interpretability tools are now being used to delve deeper into the operation of these methods, which is why this work advocates their integration in the PAD scenario. Building upon previous work, a face PAD model based on convolutional neural networks was implemented and evaluated both through traditional PAD metrics and with interpretability tools. An evaluation on the stability of the explanations obtained from testing models with attacks known and unknown in the learning step is made. To overcome the limitations of direct comparison, a suitable representation of the explanations is constructed to quantify how much two explanations differ from each other. From the point of view of interpretability, the results obtained in intra and inter class comparisons led to the conclusion that the presence of more attacks during training has a positive effect in the generalisation and robustness of the models. This is an exploratory study that confirms the urge to establish new approaches in biometrics that incorporate interpretability tools. Moreover, there is a need for methodologies to assess and compare the quality of explanations.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

“…This research proposes a novel network named Spoof Trace Disentanglement Network (STDN) to solve the challenging problem of disentangling spoof traces from faces into a hierarchical representation [18]. The research reconstructed the live counterpart and synthesized a new spoof from the live one using the spoof traces.…”

Section: ) Spoof Trace Disentanglement Network (Stdn)mentioning

confidence: 99%

A Review on Face Anti-Spoofing

Perdana

Ardiyanto

Nugroho

2021

IJITEE

View full text Add to dashboard Cite

The biometric system is a security technology that uses information based on a living person's characteristics to verify or recognize the identity, such as facial recognition. Face recognition has numerous applications in the real world, such as access control and surveillance. But face recognition has a security issue of spoofing. A face anti-spoofing, a task to prevent fake authorization by breaching the face recognition systems using a photo, video, mask, or a different substitute for an authorized person's face, is used to overcome this challenge. There is also increasing research of new datasets by providing new types of attack or diversity to reach a better generalization. This paper review of the recent development includes a general understanding of face spoofing, anti-spoofing methods, and the latest development to solve the problem against various spoof types.

show abstract

On Disentangling Spoof Trace for Generic Face Anti-spoofing

Cited by 110 publications

References 41 publications

Revisiting Pixel-Wise Supervision for Face Anti-Spoofing

Revisiting Pixel-Wise Supervision for Face Anti-Spoofing

An exploratory study of interpretability for face presentation attack detection

A Review on Face Anti-Spoofing

Contact Info

Product

Resources

About