Dual Spoof Disentanglement Generation for Face Anti-Spoofing With Depth Uncertainty Learning

  title={Dual Spoof Disentanglement Generation for Face Anti-Spoofing With Depth Uncertainty Learning},
  author={Hangtong Wu and Dan Zeng and Yibo Hu and Hailin Shi and Tao Mei},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  • Hangtong WuDan Zeng Tao Mei
  • Published 1 December 2021
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance, which limits the generalization ability of FAS model. In this paper, we propose Dual Spoof Disentanglement Generation (DSDG) framework to tackle this challenge by “anti-spoofing via generation”. Depending on the interpretable factorized latent disentanglement in Variational… 

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

A multi-modal disentanglement model is presented which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection and favorably contributes to anti-spoofing with more per- ceptible and interpretable results.

Deep Learning for Face Anti-Spoofing: A Survey

This paper presents the first comprehensive review of recent advances in deep learning based FAS, and collects and analyzes the latest methods specially designed for domain generalization and open-set FAS.

Consistency Regularization for Deep Face Anti-Spoofing

This paper enhances both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS by designing a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion.

Post-Train Adaptive MobileNet for Fast Anti-Spoofing (keynote)

The proposed Post-Train Adaptive (PTA) block is simple in structure and offers a drop-in replacement for the MobileNetV2 Inverted Residual block, offering different inference times and configuration capability for multiple device tiers.

Exploring Depth Information for Face Manipulation Detection

A Face Depth Map Transformer is proposed to estimate the face depth map patch by patch from a RGB face image, which is able to capture the local depth anomaly created due to manipulation and is considered as auxiliary information to be integrated with the backbone features using a Multi-head Depth attention mechanism that is newly designed.

Uncertainty Guided Multi-View Stereo Network for Depth Estimation

An Uncertainty Guided multi-view Network (UGNet) is proposed and an uncertainty-aware loss function is introduced, which not only can infer uncertainty implicitly in an unsupervised manner but also can reduce the bad impact of high uncertainty regions and the erroneous labels in the training set during training.

Race Bias Analysis of Bona Fide Errors in face anti-spoofing

The proposed bias analysis process on a VQ-VAE based face anti-spoofing algorithm, trained on the Replay Attack and the Spoof in the Wild databases, and analysed for bias on the SiW and Racial Faces in the wild databases demonstrate that race bias is not necessarily the result of different mean response values among the various populations.

The novel viewpoint of studying the adversarial vulnerability of FAS models

This work proposes a novel framework to expose the fine-grained adversarial vulnerability of the face anti-spoofing models, which consists of a multitask module and a semantic feature augmentation (SFA) module.

Domain Adversarial Disentanglement Network With Cross-Domain Synthesis for Generalized Face Anti-Spoofing

The Domain Adversarial Disentanglement Network with Cross-Domain Synthesis (DADN-CDS) for Face Anti-Spoofing is designed, which achieves disentanglements between domain-irrelevant liveness feature and domain-related feature, so as to minimize the effect of domain information in the needed representation that is used for inference.



On Disentangling Spoof Trace for Generic Face Anti-Spoofing

This work designs a novel adversarial learning framework to disentangle the spoof traces from input faces as a hierarchical combination of patterns at multiple scales, which demonstrates superior spoof detection performance on both seen and unseen spoof scenarios while providing visually convincing estimation of spoof traces.

Face Anti-Spoofing Via Disentangled Representation Learning

A novel perspective of face anti-spoofing is proposed that disentangles the liveness features and content features from images, and theLiveness features is further used for classification, and a Convolutional Neural Network architecture is put forward.

Deep Learning for Face Anti-Spoofing: A Survey

This paper presents the first comprehensive review of recent advances in deep learning based FAS, and collects and analyzes the latest methods specially designed for domain generalization and open-set FAS.

Progressive Transfer Learning for Face Anti-Spoofing

This paper presents a semi-supervised learning based framework to tackle face spoofing attacks with only a few labeled training data and proposes an adaptive transfer mechanism to ameliorate the influence of unseen spoofing data.

Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision

This paper argues the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues, and introduces a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations.

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

A new approach to detect presentation attacks from multiple frames based on two insights, able to capture discriminative details via Residual Spatial Gradient Block (RSGB) and encode spatio-temporal information from Spatio-Temporal Propagation Module (STPM) efficiently.

Face Anti-Spoofing with Human Material Perception

The Bilateral Convolutional Networks (BCN) is proposed, which is able to capture intrinsic material-based patterns via aggregating multi-level bilateral macro- and micro- information and Multi-level Feature Refinement Module (MFRM) and multi-head supervision are utilized to learn more robust features.

Learning Meta Model for Zero- and Few-Shot Face Anti-Spoofing

A novel Adaptive Inner-update Meta Face Anti-Spoofing (AIM-FAS) method, which trains a meta-learner focusing on the task of detecting unseen spoofing types by learning from predefined living and spoofing faces and a few examples of new attacks.

Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing

A novel perspective of face anti-spoofing that focuses on the normalization selection in the feature extraction process is proposed, which adaptively selects feature normalization methods according to the inputs, aiming to learn domain-agnostic and discriminative representation.

Unsupervised Domain Adaptation for Face Anti-Spoofing

This work introduces an unsupervised domain adaptation face anti-spoofing scheme to address the real-world scenario that learns the classifier for the target domain based on training samples in a different source domain, and introduces a new database for face spoofing detection.