Structure Destruction and Content Combination for Face Anti-Spoofing

Zhang, Keyue; Yao, Taiping; Zhang, Jian; Liu, Shice; Yin, Baocai; Ding, Shouhong; Li, Jilin

doi:10.1109/ijcb52358.2021.9484395

Cited by 43 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the tables, we present our method under the name of DeepPixBis + DPS and CDCN + DPS, where DPS stands for deep patch-wise supervision. For intra-data set experiments, we also present the results of different state-of-the-art methods such as DC-CDN [31], CDCN-PS [25], and DCN [34]. Table 1 presents the obtained results on the Replay Mobile data set, 'grandtest' protocol.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Deep patch‐wise supervision for presentation attack detection

2022

View full text Add to dashboard Cite

Face recognition systems have been widely deployed in various applications, such as online banking and mobile payment. However, these systems are vulnerable to face presentation attacks, which are created by people who obtain biometric data covertly from a person or through hacked systems. In order to detect these attacks, convolutional neural networks (CNN)‐based systems have gained significant popularity recently. CNN‐based systems perform very well on intra‐data set experiments, yet they fail to generalise to the data sets that they have not been trained on. This indicates that they tend to memorise data set‐specific spoof traces. To mitigate this problem, the authors propose a Deep Patch‐wise Supervision Presentation Attack Detection (DPS‐PAD) model approach that combines pixel‐wise binary supervision with patch‐based CNN. The authors’ experiments show that the proposed patch‐based method forces the model not to memorise the background information or data set‐specific traces. The authors extensively tested the proposed method on widely used PAD data sets—Replay‐Mobile and OULU‐NPU—and on a real‐world data set that has been collected for real‐world PAD use cases. The proposed approach is found to be superior on challenging experimental setups. Namely, it achieves higher performance on OULU‐NPU protocol 3, 4 and on inter‐data set real‐world experiments.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…In Ref. [34], authors propose a Destruction and Combination Network (DCN), which utilises their structure destruction, content combination, and local relation modelling modules. The structure destruction module is similar to jigsaw puzzle pretext tasks proposed in Ref.…”

Section: Related Workmentioning

confidence: 99%

Deep patch‐wise supervision for presentation attack detection

2022

View full text Add to dashboard Cite

show abstract

“…For instance, Li et al (2018a) used the MMD distance to make features unrelated with domains. Jia et al (2020) and Yang et al (2021) introduced triplet loss (Li et al 2019a,b) and Zhang et al (2021b) even constructed a similarity matrix to constrain the distance between features. Also, many meta-learning-based methods were exploited to find a generalized space among multiple domains (Shao et al 2020;Qin et al 2020;Kim and Lee 2021;Chen et al 2021b;Wang et al 2021;Qin et al 2021).…”

Section: Related Workmentioning

confidence: 99%

Feature Generation and Hypothesis Verification for Reliable Face Anti-spoofing

Liu

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

Although existing face anti-spoofing (FAS) methods achieve high accuracy in intra-domain experiments, their effects drop severely in cross-domain scenarios because of poor generalization. Recently, multifarious techniques have been explored, such as domain generalization and representation disentanglement. However, the improvement is still limited by two issues: 1) It is difficult to perfectly map all faces to a shared feature space. If faces from unknown domains are not mapped to the known region in the shared feature space, accidentally inaccurate predictions will be obtained. 2) It is hard to completely consider various spoof traces for disentanglement. In this paper, we propose a Feature Generation and Hypothesis Verification framework to alleviate the two issues. Above all, feature generation networks which generate hypotheses of real faces and known attacks are introduced for the first time in the FAS task. Subsequently, two hypothesis verification modules are applied to judge whether the input face comes from the real-face space and the real-face distribution respectively. Furthermore, some analyses of the relationship between our framework and Bayesian uncertainty estimation are given, which provides theoretical support for reliable defense in unknown domains. Experimental results show our framework achieves promising results and outperforms the state-of-the-art approaches on extensive public datasets.

show abstract

“…We evaluate various representative algorithms on Protocol 1 and Protocol 2, including classification supervision (i.e., ResNet-50 [25], PatchNet [64], MaxVit [59]), auxiliary pixel-wise supervision (i.e., CDCN++ [80], CDCN++binarymask [75], DCN [81], DC-CDN [78]) and generative pixel-wise supervision (i.e., LGSC [19]). For a fair comparison, we do not use pre-trained models, and other parameters are reproduced according to the original works.…”

Section: Baselinesmentioning

confidence: 99%

“…Classification supervisions are easy to construct, enabling deep FAS models to converge rapidly. In contrast, pixel-wise supervision with auxiliary tasks can ex-tract more fine-grained cues, with additional information such as pseudo depth maps [65,78,80,82], binary mask maps [43,66,74], and reflection maps [30,81,84] helping to delineate local live/spoof features. Generative pixel-wise supervisions [19,42,44,54,56], which do not rely on expertdesigned guidance and offer more flexible labels, visualize spoof cues in spoof samples, thereby enhancing the interpretability of FAS tasks.…”

Section: Introductionmentioning

confidence: 99%

Multi-Modal Face Anti-Spoofing Challenge

Wei

Guo

Escalera

et al. 2020

Synthesis Lectures on Computer Vision

View full text Add to dashboard Cite

Face anti-spoofing (FAS) is an essential mechanism for safeguarding the integrity of automated face recognition systems. Despite substantial advancements, the generalization of existing approaches to real-world applications remains challenging. This limitation can be attributed to the scarcity and lack of diversity in publicly available FAS datasets, which often leads to overfitting during training or saturation during testing. In terms of quantity, the number of spoof subjects is a critical determinant. Most datasets comprise fewer than 2,000 subjects. With regard to diversity, the majority of datasets consist of spoof samples collected in controlled environments using repetitive, mechanical processes. This data collection methodology results in homogenized samples and a dearth of scenario diversity. To address these shortcomings, we introduce the Wild Face Anti-Spoofing (WFAS) dataset, a large-scale, diverse FAS dataset collected in unconstrained settings. Our dataset encompasses 853,729 images of 321,751 spoof subjects and 529,571 images of 148,169 live subjects, representing a substantial increase in quantity. Moreover, our dataset incorporates spoof data obtained from the internet, spanning a wide array of scenarios and various commercial sensors, including 17 presentation attacks (PAs) that encompass both 2D and 3D forms. This novel data collection strategy markedly enhances FAS data diversity. Leveraging the WFAS dataset and Protocol 1 (Known-Type), we host the Wild Face Anti-Spoofing Challenge at the CVPR2023 workshop. Additionally, we meticulously evaluate representative methods using Protocol 1 and Protocol 2 (Unknown-Type). Through an in-depth examination of the challenge outcomes and benchmark baselines, we provide insightful analyses and propose potential avenues for future research.

show abstract

Structure Destruction and Content Combination for Face Anti-Spoofing

Cited by 43 publications

References 24 publications

Deep patch‐wise supervision for presentation attack detection

Deep patch‐wise supervision for presentation attack detection

Feature Generation and Hypothesis Verification for Reliable Face Anti-spoofing

Multi-Modal Face Anti-Spoofing Challenge

Contact Info

Product

Resources

About