mlsanityData to 7 Oct 2026

Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment

arXiv 2303.13662 ↗First posted 23 Mar 2023cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

This work studies the generalization issue of face anti-spoofing (FAS) models on domain gaps, such as image resolution, blurriness and sensor variations. Most prior works regard domain-specific signals as a negative impact, and apply metric learning or adversarial losses to remove them from feature representation. Though learning a domain-invariant feature space is viable for the training data, we show that the feature shift still exists in an unseen test domain, which backfires on the generalizability of the classifier. In this work, instead of constructing a domain-invariant feature space, we encourage domain separability while aligning the live-to-spoof transition (i.e., the trajectory from live to spoof) to be the same for all domains. We formulate this FAS strategy of separability and alignment (SA-FAS) as a problem of invariant risk minimization (IRM), and learn domain-variant feature representation but domain-invariant classifier. We demonstrate the effectiveness of SA-FAS on challenging cross-domain FAS datasets and establish state-of-the-art performance.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 53 of its 80 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

53 of 80 references.

References · 53

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  8. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  11. 2019Invariant Risk Minimizationcited by 1,832
  12. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
38 more
  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  3. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  4. 2013Domain Generalization via Invariant Feature Representationcited by 622
  5. 2020The Risks of Invariant Risk Minimizationcited by 262
  6. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  7. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  8. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  9. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  10. 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
  11. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
  12. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  13. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  14. 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
  15. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
  16. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  17. 2015face anti-spoofing based on color texture analysiscited by 82
  18. 2014Learn Convolutional Neural Network for Face Anti-Spoofingcited by 80
  19. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
  20. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  21. 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
  22. 2022PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognitioncited by 67
  23. 2019Correlation-aware Adversarial Domain Adaptation and Generalizationcited by 65
  24. 2020Face Anti-Spoofing with Human Material Perceptioncited by 62
  25. 2020On Disentangling Spoof Trace for Generic Face Anti-Spoofingcited by 62
  26. 2018Face De-Spoofing: Anti-Spoofing via Noise Modelingcited by 60
  27. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  28. 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
  29. 2021Dual Reweighting Domain Generalization for Face Presentation Attack Detectioncited by 47
  30. 2021Generalizable Representation Learning for Mixture Domain Face Anti-Spoofingcited by 46
  31. 2016Learning Attributes Equals Multi-Source Domain Generalizationcited by 44
  32. 2020On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofingcited by 44
  33. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  34. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  35. 2020Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learningcited by 37
  36. 2020An Empirical Study of Invariant Risk Minimizationcited by 35
  37. 2022Generative Domain Adaptation for Face Anti-Spoofingcited by 33
  38. 2021Unified Detection of Digital and Physical Face Attackscited by 31

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 24; 2025: 15; 2026: 4.

47 papers.

Sort:

By area:

  1. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  2. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  3. 2024Process Reward Model with Q-Value Rankingscited by 78
  4. 2024CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofingcited by 39
  5. 2024Gradient Alignment for Cross-Domain Face Anti-Spoofingcited by 26
  6. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 21
  7. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
  8. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  9. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  10. 2024Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Cluescited by 8
  11. 2024DiffFAS: Face Anti-Spoofing via Generative Diffusion Modelscited by 7
  12. 2025Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineeringcited by 7
35 more
  1. 2024Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant Factorscited by 6
  2. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  3. 2024VIGFace: Virtual Identity Generation for Privacy-Free Face Recognitioncited by 5
  4. 2024Confidence Aware Learning for Reliable Face Anti-spoofingcited by 5
  5. 2024CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentationcited by 5
  6. 2025Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofingcited by 5
  7. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  8. 2025Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofingcited by 5
  9. 2023Fine-Grained Annotation for Face Anti-Spoofingcited by 4
  10. 2024Generalized Face Liveness Detection via De-fake Face Generatorcited by 4
  11. 2025DADM: Dual Alignment of Domain and Modality for Face Anti-spoofingcited by 4
  12. 2026Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofingcited by 4
  13. 2024Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofingcited by 3
  14. 2025InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofingcited by 3
  15. 2023TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofingcited by 2
  16. 2024Principles of Designing Robust Remote Face Anti-Spoofing Systemscited by 2
  17. 2023IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Imagescited by 1
  18. 2024Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofingcited by 1
  19. 2024G2V2former: Graph Guided Video Vision Transformer for Face Anti-Spoofingcited by 1
  20. 2024Meta Curvature-Aware Minimization for Domain Generalizationcited by 1
  21. 2025Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detectioncited by 1
  22. 2025Enhancing Learnable Descriptive Convolutional Vision Transformer for Face Anti-Spoofingcited by 1
  23. 2025Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Imagescited by 1
  24. 2025Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofingcited by 1
  25. 2025Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofingcited by 1
  26. 2026CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detectioncited by 1
  27. 2023FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detectioncited by 0
  28. 2024Advancing Cross-Domain Generalizability in Face Anti-Spoofing: Insights, Design, and Metricscited by 0
  29. 2024Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environmentscited by 0
  30. 2024AGLP: A Graph Learning Perspective for Semi-supervised Domain Adaptationcited by 0
  31. 2025Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitionscited by 0
  32. 2025Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspectivecited by 0
  33. 2025Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detectioncited by 0
  34. 2026Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversioncited by 0
  35. 2026DBCF: Dual-Branch Complementary Fusion of Foundation Models for Generalized Deepfake Detectioncited by 0