Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Test-Time Domain Generalization for Face Anti-Spoofing (2403.19334v1)

Published 28 Mar 2024 in cs.CV

Abstract: Face Anti-Spoofing (FAS) is pivotal in safeguarding facial recognition systems against presentation attacks. While domain generalization (DG) methods have been developed to enhance FAS performance, they predominantly focus on learning domain-invariant features during training, which may not guarantee generalizability to unseen data that differs largely from the source distributions. Our insight is that testing data can serve as a valuable resource to enhance the generalizability beyond mere evaluation for DG FAS. In this paper, we introduce a novel Test-Time Domain Generalization (TTDG) framework for FAS, which leverages the testing data to boost the model's generalizability. Our method, consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS), effectively projects the unseen data to the seen domain space. In particular, we first introduce the innovative TTSP to project the styles of the arbitrarily unseen samples of the testing distribution to the known source space of the training distributions. We then design the efficient DSSS to synthesize diverse style shifts via learnable style bases with two specifically designed losses in a hyperspherical feature space. Our method eliminates the need for model updates at the test time and can be seamlessly integrated into not only the CNN but also ViT backbones. Comprehensive experiments on widely used cross-domain FAS benchmarks demonstrate our method's state-of-the-art performance and effectiveness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (121)
  1. Generalizing to unseen domains via distribution matching. arXiv preprint arXiv:1911.00804, 2019.
  2. Face anti-spoofing using patch and depth-based cnns. In IEEE International Joint Conference on Biometrics (IJCB), pages 319–328, 2017.
  3. A theory of learning from different domains. Machine learning (ML), 79:151–175, 2010.
  4. Face anti-spoofing based on color texture analysis. In IEEE International Conference on Image Processing (ICIP), pages 2636–2640, 2015.
  5. Face spoofing detection using colour texture analysis. IEEE Transactions on Information Forensics and Security (TIFS), 11(8):1818–1830, 2017a.
  6. Oulu-npu: A mobile face presentation attack database with real-world variations. In 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG), pages 612–618, 2017b.
  7. Learning meta pattern for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 17:1201–1213, 2022.
  8. Contrastive test-time adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 295–305, 2022.
  9. Generalizable representation learning for mixture domain face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 1132–1139, 2021.
  10. On the effectiveness of local binary patterns in face anti-spoofing. In International Conference of Biometrics Special Interest Group (BIOSIG), pages 1–7, 2012.
  11. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4690–4699, 2019.
  12. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR), 2020.
  13. Energy-based domain generalization for face anti-spoofing. In Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), pages 1749–1757, 2022.
  14. Integration of image quality and motion cues for face anti-spoofing: A neural network approach. Journal of Visual Communication and Image Representation (JVCIR), 38:451–460, 2016.
  15. Joint 3d face reconstruction and dense alignment with position map regression network. In European Conference on Computer Vision (ECCV), pages 534–551, 2018.
  16. Dmt: Dynamic mutual training for semi-supervised learning. Pattern Recognition (PR), page 108777, 2022.
  17. Face liveness detection using dynamic texture. Eurasip Journal on Image and Video Processing (JIVP), 2014(1):1–15, 2014.
  18. Lbp- top based countermeasure against face spoofing attacks. In Asian Conference on Computer Vision (ACCV), pages 121–132, 2012.
  19. Unsupervised domain adaptation by backpropagation. In International Conference on Machine Learning (ICML), pages 1180–1189, 2015.
  20. On the effectiveness of vision transformers for zero-shot face anti-spoofing. In IEEE International Joint Conference on Biometrics (IJCB), pages 1–8, 2021.
  21. Pit: Position-invariant transform for cross-fov domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 8761–8770, 2021.
  22. Label-free regional consistency for image-to-image translation. In IEEE International Conference on Multimedia and Expo (ICME), pages 1–6, 2021.
  23. Domain-generalized face anti-spoofing with unknown attacks. In IEEE International Conference on Image Processing (ICIP), pages 820–824, 2023.
  24. Structure destruction and content combination for generalizable anti-spoofing. IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 4(4):508–521, 2022.
  25. Rethinking generalizable face anti-spoofing via hierarchical prototype-guided distribution refinement in hyperbolic space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024a.
  26. Domain-hallucinated updating for multi-domain face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 2193–2201, 2024b.
  27. Adaptive transformers for robust few-shot cross-domain face anti-spoofing. In European Conference on Computer Vision (ECCV), pages 37–54, 2022.
  28. Ldcformer: Incorporating learnable descriptive convolution to vision transformer for face anti-spoofing. In IEEE International Conference on Image Processing (ICIP), pages 121–125, 2023a.
  29. Style projected clustering for domain generalized semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3061–3071, 2023b.
  30. Single-side domain generalization for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8484–8493, 2020.
  31. Dual-branch meta-learning network with distribution alignment for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 17:138–151, 2021a.
  32. Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing. Pattern Recognition (PR), 115:107888, 2021b.
  33. Domain-conditioned normalization for test-time domain generalization. In European Conference on Computer Vision (ECCV), pages 291–307, 2022.
  34. Face de-spoofing: Anti-spoofing via noise modeling. In European Conference on Computer Vision (ECCV), pages 290–306, 2018.
  35. The megaface benchmark: 1 million faces for recognition at scale. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4873–4882, 2016.
  36. Basn: Enriching feature representation using bipartite auxiliary supervisions for face anti-spoofing. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pages 494–503, 2019.
  37. Style-guided domain adaptation for face presentation attack detection. arXiv preprint arXiv:2203.14565, 2022.
  38. Style selective normalization with meta learning for test-time adaptive face anti-spoofing. Expert Systems with Applications (ESWA), 214:119106, 2023.
  39. Context based face anti-spoofing. In IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), pages 1–8, 2013.
  40. Liveness score-based regression neural networks for face anti-spoofing. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023.
  41. Gradient alignment for cross-domain face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  42. Learning to generalize: Meta-learning for domain generalization. In Proceedings of the AAAI conference on artificial intelligence (AAAI), pages 3490–3497, 2018a.
  43. Unsupervised domain adaptation for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 13(7):1794–1809, 2018b.
  44. Domain generalization with adversarial feature learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5400–5409, 2018c.
  45. An original face anti-spoofing approach using partial convolutional neural network. In International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–6, 2016.
  46. Spherical confidence learning for face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 15629–15637, 2021.
  47. Domain invariant vision transformer learning for face anti-spoofing. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 6098–6107, 2023.
  48. Face liveness detection by rppg features and contextual patch-based cnn. In Proceedings of the 3rd International Conference on Biometric Engineering and Applications (ICBEA), pages 61–68, 2019.
  49. Suppress and rebalance: Towards generalized multi-modal face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  50. Ma-vit: Modality-agnostic vision transformers for face anti-spoofing. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, (IJCAI), pages 1180–1186, 2022.
  51. Face anti-spoofing via adversarial cross-modality translation. IEEE Transactions on Information Forensics and Security (TIFS), 16:2759–2772, 2021a.
  52. Fm-vit: Flexible modal vision transformers for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 18:4775–4786, 2023a.
  53. Cloudmix: Dual mixup consistency for unpaired point cloud completion. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2024a.
  54. Adaptive normalized representation learning for generalizable face anti-spoofing. In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), pages 1469–1477, 2021b.
  55. Dual reweighting domain generalization for face presentation attack detection. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), pages 867–873, 2021c.
  56. Feature generation and hypothesis verification for reliable face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 1782–1791, 2022a.
  57. Spoof trace disentanglement for generic face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(3):3813–3830, 2022.
  58. Learning deep models for face anti-spoofing: Binary or auxiliary supervision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 389–398, 2018.
  59. Deep tree learning for zero-shot face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4680–4689, 2019.
  60. On disentangling spoof trace for generic face anti-spoofing. In European Conference on Computer Vision (ECCV), pages 406–422, 2020.
  61. Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing. In European Conference on Computer Vision (ECCV), pages 511–528, 2022b.
  62. Causal intervention for generalizable face anti-spoofing. In IEEE International Conference on Multimedia and Expo (ICME), pages 01–06, 2022c.
  63. Towards unsupervised domain generalization for face anti-spoofing. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 20654–20664, 2023b.
  64. Source-free domain adaptation with domain generalized pretraining for face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024b.
  65. Diverse target and contribution scheduling for domain generalization. arXiv preprint arXiv:2309.16460, 2023a.
  66. Rethinking domain generalization: Discriminability and generalizability. arXiv preprint arXiv:2309.16483, 2023b.
  67. Face spoofing detection from single images using micro-texture analysis. In International Joint Conference on Biometrics (IJCB), pages 1–7, 2011.
  68. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178, 2021.
  69. Efficient test-time model adaptation without forgetting. In International Conference on Machine Learning (ICML), pages 16888–16905, 2022.
  70. Unsupervised compound domain adaptation for face anti-spoofing. In 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG), pages 1–8, 2021.
  71. Test-time style shifting: Handling arbitrary styles in domain generalization. In Proceedings of the 40th International Conference on Machine Learning (ICML), pages 27114–27131, 2023.
  72. Secure face unlock: Spoof detection on smartphones. IEEE Transactions on Information Forensics and Security (TIFS), 11(10):2268–2283, 2016a.
  73. Cross-database face antispoofing with robust feature representation. In Chinese Conference on Biometric Recognition (CCBR), pages 611–619, 2016b.
  74. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems (NeurIPS), 30, 2017.
  75. Meta-teacher for face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(10):6311–6326, 2021.
  76. Multi-adversarial discriminative deep domain generalization for face presentation attack detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10023–10031, 2019.
  77. Regularized fine-grained meta face anti-spoofing. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 11974–11981, 2020.
  78. Ba-sam: Scalable bias-mode attention mask for segment anything model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024a.
  79. Simada: A simple unified framework for adapting segment anything model in underperformed scenes. arXiv preprint arXiv:2401.17803, 2024b.
  80. Rethinking domain generalization for face anti-spoofing: Separability and alignment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 24563–24574, 2023.
  81. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning (ICML), pages 10347–10357, 2021.
  82. Adversarial discriminative domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 7167–7176, 2017.
  83. SS Vallender. Calculation of the wasserstein distance between probability distributions on the line. Theory of Probability & Its Applications, 18(4):784–786, 1974.
  84. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research (JMLR), 9(11), 2008.
  85. Patchnet: A simple face anti-spoofing framework via fine-grained patch recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20281–20290, 2022a.
  86. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726, 2020a.
  87. Unsupervised adversarial domain adaptation for cross-domain face presentation attack detection. IEEE Transactions on Information Forensics and Security (TIFS), 16:56–69, 2021a.
  88. Facex-zoo: A pytorch toolbox for face recognition. In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), pages 3779–3782, 2021b.
  89. Self-domain adaptation for face anti-spoofing. In Proceedings of the AAAI conference on artificial intelligence (AAAI), pages 2746–2754, 2021c.
  90. Vlad-vsa: Cross-domain face presentation attack detection with vocabulary separation and adaptation. In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), pages 1497–1506, 2021d.
  91. Continual test-time domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7201–7211, 2022b.
  92. From rgb to depth: domain transfer network for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 16:4280–4290, 2021e.
  93. Deep spatial gradient and temporal depth learning for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5042–5051, 2020b.
  94. Face anti-spoofing using transformers with relation-aware mechanism. IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 4(3):439–450, 2022c.
  95. Learning multi-granularity temporal characteristics for face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 17:1254–1269, 2022d.
  96. Domain generalization via shuffled style assembly for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4123–4133, 2022e.
  97. Consistency regularization for deep face anti-spoofing. IEEE Transactions on Information Forensics and Security (TIFS), 18:1127–1140, 2023.
  98. Face spoof detection with image distortion analysis. IEEE Transactions on Information Forensics and Securityn (TIFS), 10(4):746–761, 2015.
  99. Dual spoof disentanglement generation for face anti-spoofing with depth uncertainty learning. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 32(7):4626–4638, 2021.
  100. Single-shot face anti-spoofing for dual pixel camera. IEEE Transactions on Information Forensics and Security (TIFS), 16:1440–1451, 2020.
  101. Semi-supervised 3d object detection via adaptive pseudo-labeling. In IEEE International Conference on Image Processing (ICIP), pages 3183–3187, 2021.
  102. Face liveness detection with component dependent descriptor. In IEEE International Conference on Biometrics (ICB), pages 1–6, 2013.
  103. Learn convolutional neural network for face anti-spoofing. In arXiv preprint arXiv:1408.5601, 2014.
  104. Face anti-spoofing with human material perception. In European Conference on Computer Vision (ECCV), pages 557–575, 2020a.
  105. Nas-fas: Static-dynamic central difference network search for face anti-spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(9):3005–3023, 2020b.
  106. Searching central difference convolutional networks for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5295–5305, 2020c.
  107. Revisiting pixel-wise supervision for face anti-spoofing. IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 3(3):285–295, 2021a.
  108. Dual-cross central difference network for face anti-spoofing. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), pages 1281–1287, 2021b.
  109. Face anti-spoofing via disentangled representation learning. In European Conference on Computer Vision (ECCV), pages 641–657, 2020.
  110. Structure destruction and content combination for face anti-spoofing. In IEEE International Joint Conference on Biometrics (IJCB), pages 1–6, 2021.
  111. Memo: Test time robustness via adaptation and augmentation. Advances in Neural Information Processing Systems (NeurIPS), 35:38629–38642, 2022.
  112. A face antispoofing database with diverse attacks. In 5th IAPR International Conference on Biometrics (ICB), pages 26–31, 2012.
  113. Test-time fourier style calibration for domain generalization. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI), pages 1721–1727, 2022.
  114. Learning causal representations for generalizable face anti spoofing. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5, 2023.
  115. Uncertainty-aware consistency regularization for cross-domain semantic segmentation. Computer Vision and Image Understanding (CVIU), page 103448, 2022a.
  116. Adaptive mixture of experts learning for generalizable face anti-spoofing. In Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), pages 6009–6018, 2022b.
  117. Generative domain adaptation for face anti-spoofing. In European Conference on Computer Vision (ECCV), pages 335–356, 2022c.
  118. Domain adaptive semantic segmentation with regional contrastive consistency regularization. In IEEE International Conference on Multimedia and Expo (ICME), 2022d.
  119. Context-aware mixup for domain adaptive semantic segmentation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 33(2):804–817, 2023a.
  120. Self-adversarial disentangling for specific domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(7):8954–8968, 2023b.
  121. Instance-aware domain generalization for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20453–20463, 2023c.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Qianyu Zhou (40 papers)
  2. Ke-Yue Zhang (14 papers)
  3. Taiping Yao (40 papers)
  4. Xuequan Lu (77 papers)
  5. Shouhong Ding (90 papers)
  6. Lizhuang Ma (145 papers)
Citations (11)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube