Face recognition systems are vulnerable to malicious attacks. For instance, printed photographs, replayed videos, and 3D masks of the genuine user's face can fool facial recognition systems and provide full access to the at­tacker. Traditional approaches for face presentation attack detection as­sume that training and testing data come from the same probability distri­bution. As a result, these methods’ performance drops drastically on un­seen scenarios because the learned representations may overfit the domain­-specific features in the training set. In light of this, we propose P­UDA, a patch-­based classifier framework with unsupervised domain adaptation to improve the generalization ability of face presentation attack detection. P­UDA consists of three components: Patch­-Net, MMD­ Module, and CC-­Net. Patch­-Net prevents the model from learning subject features rather than spoofing discriminative features by classifying using local patches. Secondly, MMD ­Module maps the source and target databases to a space where the Maximum Mean Discrepancy (MMD) is minimized such that a more generalized feature extractor can be learned. Finally, we attempt to learn features for real and spoof faces in the target domain without requir­ing access to the labels. Thus, we implement CC­-Net to predict the target domain database’s labels and minimize its cross-­class confusion. The pro­posed approach achieves an intra­-database Half Total Error Rate (HTER) of 0.0% in Idiap dataset. We demonstrate that our model achieves state­ of ­the ­art results in both intra-database and cross-­database testing scenarios.

[1] L. Van der Maaten and G. Hinton, “Visualizing data using tsne.,” Journal of machine learning research, vol. 9, no. 11, 2008.
[2] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Proceedings of the 25th International Conference on Neural Information Processing Systems Volume 1, NIPS’12, (Red Hook, NY, USA), p. 1097–1105, 2012.
[3] G. Wang, H. Han, S. Shan, and X. Chen, “Cross-domain face presentation attack detection via multidomain disentangled representation learning,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6677–6686, 2020.
[4] J. Yang, Z. Lei, D. Yi, and S. Z. Li, “Person-specific face anti-spoofing with subject domain adaptation,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 4, pp. 797–809, 2015.
[5] K.Y. Zhang, T. Yao, J. Zhang, Y. Tai, S. Ding, J. Li, F. Huang, H. Song, and L. Ma, “Face anti-spoofing via disentangled representation learning,” in European Conference on Computer Vision, pp. 641–657, Springer, 2020.
[6] W. M. Kouw and M. Loog, “A review of domain adaptation without target labels,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 3, pp. 766–785, 2021.
[7] S. Ben David, J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. Vaughan, “A theory of learning from different domains,” Machine Learning, vol. 79, pp. 151–175, 2010.
[8] A. Gretton, K. Borgwardt, M. Rasch, B. Schölkopf, and A. Smola, “A kernel two sample test,” The Journal of Machine Learning Research, vol. 13, pp. 723–773, 03 2012.
[9] Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A face anti-spoofing database with diverse attacks,” in 2012 5th IAPR International Conference on Biometrics (ICB), pp. 26–31, 2012.
[10] I. Chingovska, A. Anjos, and S. Marcel, “On the effectiveness of local binary patterns in face anti-spoofing,” in 2012 BIOSIG proceedings of the international conference of biometrics special interest group (BIOSIG), pp. 1–7, IEEE, 2012.
[11] Z. Boulkenafet, J. Komulainen, L. Li, X. Feng, and A. Hadid, “Oulunpu: A mobile face presentation attack database with real-world variations,” in 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017), pp. 612–618, 2017.
[12] Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face anti-spoofing using speeded up robust features and fisher vector encoding,” IEEE Signal Processing Letters, vol. 24, no. 2, pp. 141–145, 2017.
[13] J. Komulainen, A. Hadid, and M. Pietikäinen, “Context-based face antispoofing,” in 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp. 1–8, 2013.
[14] K. Patel, H. Han, A. K. Jain, and G. Ott, “Live face video vs. spoof face video: Use of moiré patterns to detect replay video attacks,” in 2015 International Conference on Biometrics (ICB), pp. 98–105, 2015.
[15] J. Määttä, A. Hadid, and M. Pietikäinen, “Face spoofing detection from single images using micro-texture analysis,” in 2011 International Joint Conference on Biometrics (IJCB), pp. 1–7, 2011.
[16] X. Tan, Y. Li, J. Liu, and L. Jiang, “Face liveness detection from a single image with sparse low-rank bilinear discriminative model,” in Computer Vision – ECCV 2010 (K. Daniilidis, P. Maragos, and N. Paragios, eds.), pp. 504–517, 2010.
[17] K. Patel, H. Han, and A. K. Jain, “Secure face unlock: Spoof detection on smartphones,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 10, pp. 2268–2283, 2016.
[18] Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face anti-spoofing based on color texture analysis,” in 2015 IEEE International Conference on Image Processing (ICIP), pp. 2636–2640, 2015.
[19] A. Anjos, M. Chakka, and S. Marcel, “Motion-based countermeasures to photo attacks in face recognition,” Biometrics, IET, vol. 3, pp. 147–158, 09 2014.
[20] L. Sun, G. Pan, Z. Wu, and S. Lao, “Blinking-based live face detection using conditional random fields,” in Advances in Biometrics (S.W. Lee and S. Z. Li, eds.), pp. 252–260, 2007.
[21] G. Pan, L. Sun, Z. Wu, and S. Lao, “Eyeblink-based anti-spoofing in face recognition from a generic web camera,” in 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8, 2007.
[22] G. Chetty, “Biometric liveness checking using multimodal fuzzy fusion,” in International Conference on Fuzzy Systems, pp. 1–8, 2010.
[23] Z. Xu, S. Li, and W. Deng, “Learning temporal features using lstm-cnn architecture for face anti-spoofing,”
in 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 141–145, 2015.
[24] R. Shao, X. Lan, and P. C. Yuen, “Deep convolutional dynamic texture learning with adaptive channel-discriminability for 3d mask face anti-spoofing,” in 2017 IEEE International Joint Conference on Biometrics (IJCB), pp. 748–755, 2017.
[25] Y. Liu, A. Jourabloo, and X. Liu, “Learning deep models for face anti-spoofing: Binary or auxiliary supervision,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 389 – 398, 2018.
[26] T. Kim, Y. Kim, I. Kim, and D. Kim, “Basn: Enriching feature representation using bipartite auxiliary supervisions for face anti-spoofing,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 494–503, 2019.
[27] X. Yang, W. Luo, L. Bao, Y. Gao, D. Gong, S. Zheng, Z. Li, and W. Liu, “Face anti-spoofing: Model matters, so does data,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3502–3511, 2019.
[28] Z. Wang, Z. Yu, C. Zhao, X. Zhu, Y. Qin, Q. Zhou, F. Zhou, and Z. Lei, “Deep spatial gradient and temporal depth learning for face anti-spoofing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5042–5051, 2020.
[29] B. Lin, X. Li, Z. Yu, and G. Zhao, “Face liveness detection by rppg features and contextual patch-based cnn,” in Proceedings of the 2019 3rd International Conference on Biometric Engineering and Applications, pp. 61–68, 2019.
[30] Z. Wang, C. Zhao, Y. Qin, Q. Zhou, G. Qi, J. Wan, and Z. Lei, “Exploiting temporal and depth information for multi-frame face anti-spoofing,” arXiv preprint arXiv:1811.05118, 2018.
[31] G. Csurka, “Domain adaptation for visual applications: A comprehensive survey,” arXiv preprint arXiv:1702.05374, 2017.
[32] I. J. Goodfellow, J. PougetAbadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” arXiv preprint arXiv:1406.2661, 2014.
[33] E. Tzeng, J. Hoffman, K. Saenko, and T. Darrell, “Adversarial discriminative domain adaptation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7167–7176, 2017.
[34] M. Long, Y. Cao, J. Wang, and M. Jordan, “Learning transferable features with deep adaptation networks,” in International conference on machine learning, pp. 97–105, PMLR, 2015.
[35] M. Ghifary, W. B. Kleijn, M. Zhang, D. Balduzzi, and W. Li, “Deep reconstruction classification networks for unsupervised domain adaptation,” in European Conference on Computer Vision, pp. 597– 613, Springer, 2016.
[36] Y. X. Lin, D. S. Tan, Y. Y. Chen, C. C. Huang, and K. L. Hua, “Domain adaptation with foreground/background cues and gated discriminators,” IEEE MultiMedia, vol. 27, no. 3, pp. 44–53, 2020.
[37] Y. Lin, D. S. Tan, W. Cheng, Y. Chen, and K. Hua, “Spatially aware domain adaptation for semantic segmentation of urban scenes,” in 2019 IEEE International Conference on Image Processing (ICIP), pp. 1870–1874, 2019.
[38] G. Wang, H. Han, S. Shan, and X. Chen, “Improving cross-database face presentation attack detection via adversarial domain adaptation,” in 2019 International Conference on Biometrics (ICB), pp. 1–8, 2019.
[39] A. George and S. Marcel, “Deep pixelwise binary supervision for face presentation attack detection,” in 2019 International Conference on Biometrics (ICB), pp. 1–8, 2019.
[40] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700–4708, 2017.
[41] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
[42] A. Smola, A. Gretton, L. Song, and B. Schölkopf, “A hilbert space embedding for distributions,” in Algorithmic Learning Theory (M. Hutter, R. A. Servedio, and E. Takimoto, eds.), (Berlin, Heidelberg), pp. 13–31, Springer Berlin Heidelberg, 2007.
[43] Y. Jin, X. Wang, M. Long, and J. Wang, “Minimum class confusion for versatile domain adaptation,” in European Conference on Computer Vision, pp. 464–480, Springer, 2020.
[44] D. E. King, “Dlib ml: A machine learning toolkit,” The Journal of Machine Learning Research, vol. 10, pp. 1755–1758, 2009.
[45] H. Li, W. Li, H. Cao, S. Wang, F. Huang, and A. C. Kot, “Unsupervised domain adaptation for face anti-spoofing,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 7, pp. 1794– 1809, 2018.
[46] J. Hu, L. Shen, and G. Sun, “Squeeze and excitation networks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141, 2018.
[47] L. Hu, M. Kan, S. Shan, and X. Chen, “Duplex generative adversarial network for unsupervised domain adaptation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1498–1507, 2018.