EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofing
Not on the map. Why?
Abstract (arXiv)
The face anti-spoofing (FAS) method performs well under intra-domain setups. However, its cross-domain performance is unsatisfactory. As a result, the domain generalization (DG) method has gained more attention in FAS. Existing methods treat FAS as a simple binary classification task and propose a heuristic training objective to learn domain-invariant features. However, there is no theoretical explanation of what a domain-invariant feature is. Additionally, the lack of theoretical support makes domain generalization techniques such as adversarial training lack training stability. To address these issues, this paper proposes the EnfoMax framework, which uses information theory to analyze cross-domain FAS tasks. This framework provides theoretical guarantees and optimization objectives for domain-generalized FAS tasks. EnfoMax maximizes the domain entropy and mutual information of live samples in source domains without using adversarial learning. Experimental results demonstrate that our approach performs well on extensive public datasets and outperforms state-of-the-art methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 90 references that are in the map. First posted on arXiv 17 Feb 2023.
Builds on
43 of 90 references.
References · 43
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020Supervised Contrastive Learningcited by 2,803
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2019Invariant Risk Minimizationcited by 1,832
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2020What Makes for Good Views for Contrastive Learning?cited by 843
31 more
- 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
- 2018MINE: Mutual Information Neural Estimationcited by 680
- 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
- 2019On Variational Bounds of Mutual Informationcited by 550
- 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
- 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
- 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
- 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
- 2018Invariant Representations without Adversarial Trainingcited by 111
- 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
- 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
- 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
- 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
- 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
- 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
- 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
- 2022PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognitioncited by 67
- 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
- 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
- 2021Dual Reweighting Domain Generalization for Face Presentation Attack Detectioncited by 47
- 2021Generalizable Representation Learning for Mixture Domain Face Anti-Spoofingcited by 46
- 2019Learning Meta Model for Zero- and Few-shot Face Anti-spoofingcited by 44
- 2020On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofingcited by 44
- 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
- 2020Respecting Domain Relations: Hypothesis Invariance for Domain Generalizationcited by 30
- 2020Learning Unbiased Representations via Mutual Information Backpropagationcited by 25
- 20203D Face Anti-spoofing with Factorized Bilinear Codingcited by 20
- 2021Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learningcited by 20
- 2023Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofingcited by 19
- 2022Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domainscited by 10
- 2021Few-Shot Domain Expansion for Face Anti-Spoofingcited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.