臺灣博碩士論文加值系統

現在已經有許多人臉反欺騙方法來應對各種偽冒攻擊，並取得了不錯的性能。
儘管現有方法在數據集內場景上運行良好，但在處理看不見的場景時性能下降。
因此，在本篇論文中，我們專注在人臉反欺騙問題的域泛化，並提出了一種新的
圖片增強策略來增加數據多樣性。與幾種區域隨機遮擋的區域丟失策略不同，本
篇所提出的增強策略增加了激活值較低的補丁區域以生成更具挑戰性的圖像。此
外，我們將域對抗學習模塊與三元組挖掘相結合，以提取域不變的活性特徵，並
為看不見的域學習更好的類邊界。此外，還進一步結合了像素級監督，以輔助人
臉反欺騙模型通過估計像素因素來學習判別特徵。在幾個基準數據集上的廣泛實
驗結果證明了我們方法的有效性，並顯示出對最先進的競爭對手的顯著改進。

Many face anti-spoofing methods have been developed to counter diverse presentation
attacks and achieved promising performance. Despite existing methods
work well on the intra-dataset scenarios, the performance drops when dealing with
the unseen scenarios. In this paper, we focus on domain generalization for face antispoofing
(FAS) problem and propose a novel augmentation strategy to increase the
data diversity. Unlike several regional dropout strategies, where the region are
random occluded, the proposed augmentation strategy increase the patch area with
lower activation value to generate more challenging images. Moreover, we combine
Domain Adversarial Learning Module (DALM) with triplet mining to extract
domain-invariant liveness features and learn a better class boundary for unseen domains.
Additionally, the pixel-level supervision is further incorporated to guide the
face anti-spoofing model to learn discriminative features by estimating pixel-wise
factors. Extensive experimental results on several benchmark datasets prove that
our method show significant improvement over the state-of-the-art competitors.

摘要i
Abstract ii
Acknowledgements
1 Introduction 1
2 Related Work 4
2.1 Face Anti-spoofing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1.1 Depth-based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1.2 Temporal-based Methods . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.2 Data Augmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.3 Domain Generalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3 Method 7
3.1 Problem Definition and Notations . . . . . . . . . . . . . . . . . . . . . . . . 7
3.2 Data Augmentation Strategy . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.2.1 Obtain the Combined Face Image and Activation Map . . . . . . . . . 9
3.2.2 Crop and Paste . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2.3 Augmented Images of Two Different Cases . . . . . . . . . . . . . . . 11
3.3 Domain Adversarial Learning Module . . . . . . . . . . . . . . . . . . . . . . 12
3.4 Triplet Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.5 Pixel-level Supervision . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.6 Total Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4 Experiments 16
4.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.2 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.3 Evaluation metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.4 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.5 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.5.1 Experiment on Leave-one-out Setting . . . . . . . . . . . . . . . . . . 21
4.5.2 Experiment on Limited Source Domains . . . . . . . . . . . . . . . . . 22
4.5.3 Visualization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.6 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
5 Conclusion 25

[1] Y. Liu, A. Jourabloo, and X. Liu, “Learning deep models for face anti-spoofing: Binary
or auxiliary supervision,” in Proceedings of the IEEE conference on computer vision and
pattern recognition, pp. 389–398, 2018.
[2] A. Jourabloo, Y. Liu, and X. Liu, “Face de-spoofing: Anti-spoofing via noise modeling,”
in Proceedings of the European Conference on Computer Vision (ECCV), pp. 290–306,
2018.
[3] Y. Liu, J. Stehouwer, A. Jourabloo, and X. Liu, “Deep tree learning for zero-shot face antispoofing,”
in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition, pp. 4680–4689, 2019.
[4] X. Yang, W. Luo, L. Bao, Y. Gao, D. Gong, S. Zheng, Z. Li, and W. Liu, “Face antispoofing:
Model matters, so does data,” in Proceedings of the IEEE/CVF Conference on
Computer Vision and Pattern Recognition, pp. 3507–3516, 2019.
[5] 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.
[6] Z. Yu, X. Li, X. Niu, J. Shi, and G. Zhao, “Face anti-spoofing with human material perception,”
in European Conference on Computer Vision, pp. 557–575, Springer, 2020.
[7] 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.
[8] Y. Liu, J. Stehouwer, and X. Liu, “On disentangling spoof trace for generic face antispoofing,”
in European Conference on Computer Vision, pp. 406–422, Springer, 2020.
[9] H. Feng, Z. Hong, H. Yue, Y. Chen, K. Wang, J. Han, J. Liu, and E. Ding, “Learning
generalized spoof cues for face anti-spoofing,” arXiv preprint arXiv:2005.03922, 2020.
[10] K.-Y. Zhang, T. Yao, J. Zhang, S. Liu, B. Yin, S. Ding, and J. Li, “Structure destruction and
content combination for face anti-spoofing,” in 2021 IEEE International Joint Conference
on Biometrics (IJCB), pp. 1–6, IEEE, 2021.
[11] Y.-C. Wang, C.-Y. Wang, and S.-H. Lai, “Disentangled representation with dual-stage feature
learning for face anti-spoofing,” in Proceedings of the IEEE/CVF Winter Conference
on Applications of Computer Vision, pp. 1955–1964, 2022.
[12] S. Shankar, V. Piratla, S. Chakrabarti, S. Chaudhuri, P. Jyothi, and S. Sarawagi, “Generalizing
across domains via cross-gradient training,” arXiv preprint arXiv:1804.10745,
2018.
[13] R. Volpi, H. Namkoong, O. Sener, J. C. Duchi, V. Murino, and S. Savarese, “Generalizing
to unseen domains via adversarial data augmentation,” Advances in neural information
processing systems, vol. 31, 2018.
[14] M. Mancini, Z. Akata, E. Ricci, and B. Caputo, “Towards recognizing unseen categories
in unseen domains,” in European Conference on Computer Vision, pp. 466–483, Springer,
2020.
[15] T. DeVries and G. W. Taylor, “Improved regularization of convolutional neural networks
with cutout,” arXiv preprint arXiv:1708.04552, 2017.
[16] G. Ghiasi, T.-Y. Lin, and Q. V. Le, “Dropblock: A regularization method for convolutional
networks,” Advances in neural information processing systems, vol. 31, 2018.
[17] S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, “Cutmix: Regularization strategy
to train strong classifiers with localizable features,” in Proceedings of the IEEE/CVF
international conference on computer vision, pp. 6023–6032, 2019.
[18] R. Shao, X. Lan, J. Li, and P. C. Yuen, “Multi-adversarial discriminative deep domain
generalization for face presentation attack detection,” in Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, pp. 10023–10031, 2019.
[19] G. Wang, H. Han, S. Shan, and X. Chen, “Cross-domain face presentation attack detection
via multi-domain disentangled representation learning,” in Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, pp. 6678–6687, 2020.
[20] Y. Jia, J. Zhang, S. Shan, and X. Chen, “Single-side domain generalization for face antispoofing,”
in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition, pp. 8484–8493, 2020.
[21] R. Shao, X. Lan, and P. C. Yuen, “Regularized fine-grained meta face anti-spoofing,” in
Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11974–11981,
2020.
[22] S. Saha, W. Xu, M. Kanakis, S. Georgoulis, Y. Chen, D. P. Paudel, and L. Van Gool,
“Domain agnostic feature learning for image and video based face anti-spoofing,” in Proceedings
of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,
pp. 802–803, 2020.
[23] Z. Yu, J. Wan, Y. Qin, X. Li, S. Z. Li, and G. Zhao, “Nas-fas: Static-dynamic central
difference network search for face anti-spoofing,” IEEE transactions on pattern analysis
and machine intelligence, vol. 43, no. 9, pp. 3005–3023, 2020.
[24] S. Liu, K.-Y. Zhang, T. Yao, M. Bi, S. Ding, J. Li, F. Huang, and L. Ma, “Adaptive normalized
representation learning for generalizable face anti-spoofing,” in Proceedings of
the 29th ACM International Conference on Multimedia, pp. 1469–1477, 2021.
[25] J. Wang, J. Zhang, Y. Bian, Y. Cai, C. Wang, and S. Pu, “Self-domain adaptation for face
anti-spoofing,” arXiv preprint arXiv:2102.12129, 2021.
[26] Z. Chen, T. Yao, K. Sheng, S. Ding, Y. Tai, J. Li, F. Huang, and X. Jin, “Generalizable
representation learning for mixture domain face anti-spoofing,” arXiv preprint
arXiv:2105.02453, 2021.
[27] A. Liu, Z. Tan, J. Wan, Y. Liang, Z. Lei, G. Guo, and S. Z. Li, “Face anti-spoofing via
adversarial cross-modality translation,” IEEE Transactions on Information Forensics and
Security, vol. 16, pp. 2759–2772, 2021.
[28] Z. Huang, H. Wang, E. P. Xing, and D. Huang, “Self-challenging improves cross-domain
generalization,” in European Conference on Computer Vision, pp. 124–140, Springer,
2020.
[29] Y. Atoum, Y. Liu, A. Jourabloo, and X. Liu, “Face anti-spoofing using patch and depthbased
cnns,” in 2017 IEEE International Joint Conference on Biometrics (IJCB), pp. 319–
328, 2017.
[30] PeiKai-Huang, M.-C. Chin, and C.-T. Hsu, “Face anti-spoofing via robust auxiliary estimation
and discriminative feature learning,” in Asian Conference on Pattern Recognition,
Springer, 2021.
[31] L. Sun, G. Pan, Z. Wu, and S. Lao, “Blinking-based live face detection using conditional
random fields,” in International Conference on Biometrics, pp. 252–260, Springer, 2007.
[32] K. Kollreider, H. Fronthaler, M. I. Faraj, and J. Bigun, “Real-time face detection and
motion analysis with application in “liveness”assessment,” IEEE Transactions on Information
Forensics and Security, vol. 2, no. 3, pp. 548–558, 2007.
[33] S. Liu, P. C. Yuen, S. Zhang, and G. Zhao, “3d mask face anti-spoofing with remote photoplethysmography,”
in European Conference on Computer Vision, pp. 85–100, Springer,
2016.
[34] X. Li, J. Komulainen, G. Zhao, P.-C. Yuen, and M. Pietikäinen, “Generalized face antispoofing
by detecting pulse from face videos,” in 2016 23rd International Conference on
Pattern Recognition (ICPR), pp. 4244–4249, IEEE, 2016.
[35] S.-Q. Liu, X. Lan, and P. C. Yuen, “Remote photoplethysmography correspondence feature
for 3d mask face presentation attack detection,” in Proceedings of the European Conference
on Computer Vision (ECCV), pp. 558–573, 2018.
[36] K. Zhou, Y. Yang, T. Hospedales, and T. Xiang, “Learning to generate novel domains
for domain generalization,” in European conference on computer vision, pp. 561–578,
Springer, 2020.
[37] K. Zhou, Y. Yang, T. Hospedales, and T. Xiang, “Deep domain-adversarial image generation
for domain generalisation,” in Proceedings of the AAAI Conference on Artificial
Intelligence, vol. 34, pp. 13025–13032, 2020.
[38] K. Kumar Singh and Y. Jae Lee, “Hide-and-seek: Forcing a network to be meticulous for
weakly-supervised object and action localization,” in Proceedings of the IEEE International
Conference on Computer Vision, pp. 3524–3533, 2017.
[39] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, “Random erasing data augmentation,” in
Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp. 13001–13008,
2020.
[40] J. Choe and H. Shim, “Attention-based dropout layer for weakly supervised object localization,”
in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition, pp. 2219–2228, 2019.
[41] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a
simple way to prevent neural networks from overfitting,” The journal of machine learning
research, vol. 15, no. 1, pp. 1929–1958, 2014.
[42] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for
discriminative localization,” in Proceedings of the IEEE conference on computer vision
and pattern recognition, pp. 2921–2929, 2016.
[43] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam:
Visual explanations from deep networks via gradient-based localization,” in Proceedings
of the IEEE international conference on computer vision, pp. 618–626, 2017.
[44] Y. Ganin and V. Lempitsky, “Unsupervised domain adaptation by backpropagation,” in
International conference on machine learning, pp. 1180–1189, PMLR, 2015.
[45] Z. Boulkenafet, J. Komulainen, L. Li, X. Feng, and A. Hadid, “Oulu-npu: 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, IEEE, 2017.
[46] Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi, and S. Z. Li, “A face antispoofing database with
diverse attacks,” in 2012 5th IAPR international conference on Biometrics (ICB), pp. 26–
31, IEEE, 2012.
[47] D. Wen, H. Han, and A. K. Jain, “Face spoof detection with image distortion analysis,”
IEEE Transactions on Information Forensics and Security, vol. 10, no. 4, pp. 746–761,
2015.
[48] 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.
[49] A. Anjos and S. Marcel, “Counter-measures to photo attacks in face recognition: a public
database and a baseline,” in 2011 international joint conference on Biometrics (IJCB),
pp. 1–7, IEEE, 2011.
[50] 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, IEEE, 2011.
[51] T. d. Freitas Pereira, J. Komulainen, A. Anjos, J. M. De Martino, A. Hadid, M. Pietikäinen,
and S. Marcel, “Face liveness detection using dynamic texture,” EURASIP Journal on
Image and Video Processing, vol. 2014, no. 1, pp. 1–15, 2014.
[52] Z. Boulkenafet, J. Komulainen, and A. Hadid, “Face spoofing detection using colour texture
analysis,” IEEE Transactions on Information Forensics and Security, vol. 11, no. 8,
pp. 1818–1830, 2016.
[53] D. Li, Y. Yang, Y.-Z. Song, and T. M. Hospedales, “Learning to generalize: Meta-learning
for domain generalization,” in Thirty-Second AAAI Conference on Artificial Intelligence,
2018.
[54] Y. Balaji, S. Sankaranarayanan, and R. Chellappa, “Metareg: Towards domain generalization
using meta-regularization,” Advances in neural information processing systems,
vol. 31, 2018.
[55] H. Li, S. J. Pan, S. Wang, and A. C. Kot, “Domain generalization with adversarial feature
learning,” in Proceedings of the IEEE conference on computer vision and pattern
recognition, pp. 5400–5409, 2018.
[56] Y. He, A. Carass, L. Zuo, B. E. Dewey, and J. L. Prince, “Self domain adapted network,”
in International Conference on Medical Image Computing and Computer-Assisted Intervention,
pp. 437–446, Springer, 2020.
[57] Y. Qin, Z. Yu, L. Yan, Z. Wang, C. Zhao, and Z. Lei, “Meta-teacher for face anti-spoofing,”
IEEE transactions on pattern analysis and machine intelligence, 2021.
[58] Z. Wang, Z. Wang, Z. Yu, W. Deng, J. Li, T. Gao, and Z. Wang, “Domain generalization
via shuffled style assembly for face anti-spoofing,” in Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, pp. 4123–4133, 2022.