mlsanityData to 14 Oct 2026

Consistency Regularization for Deep Face Anti-Spoofing

arXiv 2111.12320 ↗First posted 24 Nov 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views of this image usually performs better, as shown in Fig.1. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding-level, we design a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion; while at the prediction-level, we optimize the mean square error between the predictions of two views. Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes. Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques. We conduct extensive experiments to show that EPCR can significantly improve the performance of several supervised and semi-supervised tasks on benchmark datasets. The codes and protocols will be released at https://github.com/clks-wzz/EPCR.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 58 of its 105 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

58 of 105 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  10. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  11. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  12. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
38 more
  1. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  2. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  3. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  4. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  5. 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
  6. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
  7. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  8. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 105
  9. 2018Revisiting Small Batch Training for Deep Neural Networkscited by 102
  10. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
  11. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  12. 2015face anti-spoofing based on color texture analysiscited by 82
  13. 2014Learn Convolutional Neural Network for Face Anti-Spoofingcited by 80
  14. 2019Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Networkcited by 79
  15. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
  16. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  17. 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
  18. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  19. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 65
  20. 2020Face Anti-Spoofing with Human Material Perceptioncited by 62
  21. 2020On Disentangling Spoof Trace for Generic Face Anti-Spoofingcited by 62
  22. 2018Face De-Spoofing: Anti-Spoofing via Noise Modelingcited by 60
  23. 2018A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofingcited by 51
  24. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  25. 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
  26. 2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
  27. 2021Dual Reweighting Domain Generalization for Face Presentation Attack Detectioncited by 47
  28. 2021Generalizable Representation Learning for Mixture Domain Face Anti-Spoofingcited by 46
  29. 2020Revisiting Pixel-Wise Supervision for Face Anti-Spoofingcited by 45
  30. 2019Learning Meta Model for Zero- and Few-shot Face Anti-spoofingcited by 44
  31. 2020On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofingcited by 44
  32. 2021Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detectioncited by 43
  33. 2021Cross Modal Focal Loss for RGBD Face Anti-Spoofingcited by 41
  34. 2020Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networkscited by 36
  35. 2021Detection and Continual Learning of Novel Face Presentation Attackscited by 33
  36. 2021Meta-Teacher For Face Anti-Spoofingcited by 33
  37. 2021Self-restrained Triplet Loss for Accurate Masked Face Recognitioncited by 32
  38. 2020Anomaly Detection-Based Unknown Face Presentation Attack Detectioncited by 20

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 1; 2026: 1.

10 papers.

  1. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  2. 2023S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokenscited by 11
  3. 2023Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameterscited by 9
  4. 2024DiffFAS: Face Anti-Spoofing via Generative Diffusion Modelscited by 7
  5. 2023Domain Generalization via Ensemble Stacking for Face Presentation Attack Detectioncited by 6
  6. 2023Hyperbolic Face Anti-Spoofingcited by 1
  7. 2024Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofingcited by 1
  8. 2024Advancing Cross-Domain Generalizability in Face Anti-Spoofing: Insights, Design, and Metricscited by 0
  9. 2025Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitionscited by 0
  10. 2026Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversioncited by 0