Domain Adaptation for Face Anti-Spoofing Based on Dual Disentanglement and Liveness Feature Progressive Alignment

Feng Jun; Shi Yichen; Gao Yuhao; He Jingjing; Yu Zitong

doi:10.7544/issn1000-1239.202330251

Journal of Computer Research and Development > 2023 > 60(8): 1727-1739. > DOI: 10.7544/issn1000-1239.202330251 CSTR: 32373.14.issn1000-1239.202330251

Feng Jun, Shi Yichen, Gao Yuhao, He Jingjing, Yu Zitong. Domain Adaptation for Face Anti-Spoofing Based on Dual Disentanglement and Liveness Feature Progressive Alignment[J]. Journal of Computer Research and Development, 2023, 60(8): 1727-1739. DOI: 10.7544/issn1000-1239.202330251

Citation:

PDF (2018 KB)

Domain Adaptation for Face Anti-Spoofing Based on Dual Disentanglement and Liveness Feature Progressive Alignment

1.
School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang 050043
2.
Great Bay University, Dongguan, Guangdong 523000

Funds: This work was supported by the National Natural Science Foundation of China (61772070, 61972267) and the Key Projects of Science and Technology Research in Colleges and Universities of Hebei Province (ZD2021333).

More Information

Author Bio:
Feng Jun: born in 1971. PhD, professor. Member of CCF. Her main research interests include computer vision, machine learning, and complex network analysis

Shi Yichen: born in 1998. Master. His main research interests include face anti-spoofing and transfer learning

Gao Yuhao: born in 2000. Master candidate. His main research interest includes face anti-spoofing

He Jingjing: born in 2000. Master candidate. Her main research interest includes face anti-spoofing

Yu Zitong: born in 1992. PhD, assistant professor. His main research interests include biometric recognition and multimedia security
Received Date: March 30, 2023
Revised Date: June 15, 2023
Available Online: June 26, 2023

Graphical Abstract

Abstract

Abstract

Although existing face anti-spoofing methods perform well in intra-domain testing, their performance significantly degrades in cross-domain scenarios. Current cross-domain face anti-spoofing methods based on domain adversarial alignment cannot guarantee that the alignment task directly serves the classification task since the alignment and classification networks are independent of each other. We propose a domain adaptation for face anti-spoofing method based on domain invariant liveness features dual disentanglement and progressive adversarial alignment. Firstly, the source domain features are heuristically disentangled into domain specific features and domain invariant features. Then, the gradient of classifier is used to perform a second disentanglement of the live-related and live-unrelated features in the domain invariant features. To alleviate optimization difficulties during training, a curriculum learning method is adopted to progressively align target domain features and the combination of live-related and live-unrelated features, gradually increasing the proportion of live-related features, and enhancing the correlation between the target domain features and face anti-spoofing task. From a causal perspective, we provide an explanation for the liveness alignment domain adaptation. Experimental results on CASIA-MFSD, Idiap Replay-Attack, MSU-MFSD, and OULU-NPU datasets demonstrate that the proposed method achieves the best average HTER value of 22.5% compared with ten existing methods and the current state-of-the-art performance on four evaluation protocols. Especially the HTER values of I-M and O-M evaluation protocols achieve 12.4% and 12.8%, respectively. The proposed method can significantly reduce the error rates of the model in the target domain and has better cross-domain generalization ability.
- face anti-spoofing,
- domain adaptation,
- dual disentanglement,
- domain adversarial progressive alignment,
- curriculum learning

FullText(HTML)

References (51)

References

[1]	Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research, 2016, 17(1): 1−35
[2]	De F P T, Anjos A, De M J M, et al. LBP-TOP based countermeasure against face spoofing attacks[C] //Proc of the Asian Conf on Computer Vision. Berlin: Springer, 2012: 121−132
[3]	Liu Chengjun, Wechsler H. Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition[J]. IEEE Transactions on Image Processing, 2002, 11(4): 467−476 doi: 10.1109/TIP.2002.999679
[4]	束鑫,唐慧,杨习贝,等. 基于差分量化局部二值模式的人脸反欺诈算法研究[J]. 计算机研究与发展,2020,57(7):1508−1521 doi: 10.7544/issn1000-1239.2020.20190319 Shu Xin, Tang Hui, Yang Xibei, et al. Research on face anti-spoofing algorithm based on DQ_LBP[J]. Journal of Computer Research and Development, 2020, 57(7): 1508−1521 (in Chinese) doi: 10.7544/issn1000-1239.2020.20190319
[5]	Galbally J, Marcel S, Fierrez J. Image quality assessment for fake biometric detection: Application to iris, fingerprint, and face recognition[J]. IEEE Transactions on Image Processing, 2013, 23(2): 710−724
[6]	Ikeuchi K, Miyazaki D, Tan R T, et al. Separating reflection components of textured surfaces using a single image[J]. Digitally Archiving Cultural Objects, 2008, 6(3): 353−384
[7]	Yu Zitong, Peng Wei, Li Xiaobai, et al. Remote heart rate measurement from highly compressed facial videos: An end-to-end deep learning solution with video enhancement[C] //Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 151−160
[8]	Li Xiaobai, Komulainen J, Zhao Guoying, et al. Generalized face anti-spoofing by detecting pulse from face videos[C] //Proc of the Int Conf on Pattern Recognition. Piscataway, NJ: IEEE, 2016: 4244−4249
[9]	Pan Gang, Sun Lin, Wu Zhaohui, et al. Eyeblink-based anti-spoofing in face recognition from a generic webcamera[C] //Proc of the IEEE 11th Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2007: 1−8
[10]	Pan Gang, Wu Zhaohui, Sun Lin. Liveness detection for face recognition[J]. Recent Advances in Face Recognition, 2008, 9(2): 109−124
[11]	Chingovska I, Yang Jianwei, Lei Zhen, et al. The 2nd competition on counter measures to 2D face spoofing attacks[C] //Proc of the Int Conf on Biometrics. Piscataway, NJ: IEEE, 2013: 1−6
[12]	Boulkenafet Z, Komulainen J, Hadid A. Face anti-spoofing based on color texture analysis[C] //Proc of the IEEE Int Conf on Image Processing. Piscataway, NJ: IEEE, 2015: 2636−2640
[13]	Patel K, Han H, Jain A K. Secure face unlock: Spoof detection on smartphones[J]. IEEE Transactions on Information Forensics and Security, 2016, 11(10): 2268−2283 doi: 10.1109/TIFS.2016.2578288
[14]	Boulkenafet Z, Komulainen J, Hadid A. Face antispoofing using speeded-up robust features and Fisher vector encoding[J]. IEEE Signal Processing Letters, 2016, 24(2): 141−145
[15]	Komulainen J, Hadid A, Pietikäinen M. Context based face anti-spoofing[C] //Proc of the 6th IEEE Int Conf on Biometrics: Theory, Applications and Systems . Piscataway, NJ: IEEE, 2013: 1−8
[16]	Yang Jianwei, Lei Zhen, Li S Z. Learn convolutional neural network for face anti-spoofing[J]. arXiv preprint, arXiv: 1408.5601, 2014
[17]	Liu Yaojie, Jourabloo A, Liu Xiaoming. Learning deep models for face anti-spoofing: Binary or auxiliary supervision[C] //Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 389−398
[18]	Atoum Y, Liu Yaojie, Jourabloo A, et al. Face anti-spoofing using patch and depth-based CNNs[C] //Proc of the IEEE Int Joint Conf on Biometrics. Piscataway, NJ: IEEE, 2017: 319−328
[19]	Wang Zezheng, Yu Zitong, Zhao Chenxu, et al. Deep spatial gradient and temporal depth learning for face anti-spoofing[C] //Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 5042−5051
[20]	王宏飞,程鑫,赵祥模,等. 光流与纹理特征融合的人脸活体检测算法[J]. 计算机工程与应用,2022,58(6):170−176 doi: 10.3778/j.issn.1002-8331.2108-0046 Wang Hongfei, Cheng Xin, Zhao Xiangmo, et al. Face liveness detection based on fusional optical flow and texture features[J]. Computer Engineering and Applications, 2022, 58(6): 170−176 (in Chinese) doi: 10.3778/j.issn.1002-8331.2108-0046
[21]	汪亚航,宋晓宁,吴小俊. 结合混合池化的双流人脸活体检测网络[J]. 中国图象图形学报,2020,25(7):1408−1420 Wang Yahang, Song Xiaoning, Wu Xiaojun. Two-stream face spoofing detection network combined with hybrid pooling[J]. Journal of Image and Graphics, 2020, 25(7): 1408−1420 (in Chinese)
[22]	马思源, 郑涵, 郭文. 应用深度光学应变特征图的人脸活体检测[J]. 中国图象图形学报, 2020, 25（3）: 618−628 Ma Siyuan, Zheng Han, Guo Wen. Deep optical strain feature map for face anti-spoofing[J]. Journal of Image and Graphics, 2020, 25(3): 618−628(in Chinese)
[23]	Yu Zitong, Zhao Chenxu, Wang Zezheng, et al. Searching central difference convolutional networks for face anti-spoofing[C] //Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 5295−5305
[24]	Li Haoliang, Li Wei, Cao Hong, et al. Unsupervised domain adaptation for face anti-spoofing[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(7): 1794−1809 doi: 10.1109/TIFS.2018.2801312
[25]	Gretton A, Borgwardt K M, Rasch M J, et al. A kernel two-sample test[J]. The Journal of Machine Learning Research, 2012, 13(1): 723−773
[26]	Tu Xiaoguang, Zhang Hengsheng, Xie Mei, et al. Deep transfer across domains for face anti-spoofing[J]. Journal of Electronic Imaging, 2019, 28(4): 43001
[27]	翁泽佳,陈静静,姜育刚. 基于域对抗学习的可泛化虚假人脸检测方法研究[J]. 计算机研究与发展,2021,58(7):1476−1489 doi: 10.7544/issn1000-1239.2021.20200803 Weng Zejia, Chen Jingjing, Jiang Yugang. On the generalization of face forgery detection with domain adversarial learning[J]. Journal of Computer Research and Development, 2021, 58(7): 1476−1489 (in Chinese) doi: 10.7544/issn1000-1239.2021.20200803
[28]	Kim Y E, Nam W J, Min K, et al. Style-guided domain adaptation for face presentation attack detection[J]. arXiv preprint, arXiv: 2203.14565, 2022
[29]	Hamblin J, Nikhal K, Riggan B S. Understanding cross domain presentation attack detection for visible face recognition[C] //Proc of the 16th IEEE Int Conf on Automatic Face and Gesture Recognition. Piscataway, NJ: IEEE, 2021: 1−8
[30]	Wang Guoqing, Han Hu, Shan Shiguang, et al. Improving cross-database face presentation attack detection via adversarial domain adaptation[C] //Proc of the Int Conf on Biometrics. Piscataway, NJ: IEEE, 2019: 1−8
[31]	El-Din Y S, Moustafa M N, Mahdi H. Adversarial unsupervised domain adaptation guided with deep clustering for face presentation attack detection[J]. arXiv preprint, arXiv: 2102.06864, 2021
[32]	Yang Luyu, Balaji Y, Lim S N, et al. Curriculum manager for source selection in multi-source domain adaptation[C] //Proc of the European Conf on Computer Vision. Berlin: Springer, 2020: 608−624
[33]	Shu Yang, Cao Zhangjie, Long Mingsheng, et al. Transferable curriculum for weakly-supervised domain adaptation[C] //Proc of the AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2019, 33(1): 4951−4958
[34]	Gong Chen, Tao Dacheng, Maybank S J, et al. Multi-modal curriculum learning for semi-supervised image classification[J]. IEEE Transactions on Image Processing, 2016, 25(7): 3249−3260 doi: 10.1109/TIP.2016.2563981
[35]	Wang Yiru, Gan Weihao, Yang Jie, et al. Dynamic curriculum learning for imbalanced data classification[C] //Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 5017−5026
[36]	Cui Shuhao, Jin Xuan, Wang Shuhui, et al. Heuristic domain adaptation[J]. Advances in Neural Information Processing Systems, 2020, 33: 7571−7583
[37]	Wei Guoqiang, Lan Culing, Zeng Wenjun, et al. ToAlign: Task-oriented alignment for unsupervised domain adaptation[J]. Advances in Neural Information Processing Systems, 2021, 34: 13834−13846
[38]	Selvaraju R R, Cogswell M, Das A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization[C] //Proc of the IEEE Int Conf on Computer Vision. Los Alamitos, CA: IEEE Computer Society, 2017: 618−626
[39]	Chattopadhay A, Sarkar A, Howlader P, et al. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks[C] //Proc of the IEEE Winter Conf on Applications of Computer Vision . Piscataway, NJ: IEEE, 2018: 839−847
[40]	Bengio Y, Louradour J, Collobert R, et al. Curriculum learning[C] //Proc of the 26th Annual Int Conf on Machine Learning. New York: ACM, 2009: 41−48
[41]	Zhang Zhiwei, Yan Junjie, Liu Sifei, et al. A face antispoofing database with diverse attacks[C] //Proc of the 5th IAPR Int Conf on Biometrics. Piscataway, NJ: IEEE, 2012: 26−31
[42]	Chingovska I, Anjos A, Marcel S. On the effectiveness of local binary patterns in face anti-spoofing[C] //Proc of the Int Conf of Biometrics Special Interest Group. Piscataway, NJ: IEEE, 2012: 1−7
[43]	Wen Di, Han Hu, Jain A K. Face spoof detection with image distortion analysis[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(4): 746−761 doi: 10.1109/TIFS.2015.2400395
[44]	Boulkenafet Z, Komulainen J, Li Lei, et al. OULU-NPU: A mobile face presentation attack database with real-world variations[C] //Proc of the 12th IEEE Int Conf on Automatic Face & Gesture Recognition. Piscataway, NJ: IEEE, 2017: 612−618
[45]	Yang Jianwei, Lei Zhen, Yi Dong, et al. Person-specific face antispoofing with subject domain adaptation[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(4): 797−809 doi: 10.1109/TIFS.2015.2403306
[46]	Ghifary M, Kleijn W B, Zhang M, et al. Deep reconstruction classification networks for unsupervised domain adaptation[C] //Proc of the European Conf on Computer Vision. Berlin: Springer, 2016: 597−613
[47]	Tzeng E, Hoffman J, Saenko K, et al. Adversarial discriminative domain adaptation[C] //Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 7167−7176
[48]	Wang Guoqing, Han Hu, Shan Shiguang, et al. Unsupervised adversarial domain adaptation for cross-domain face presentation attack detection[J]. IEEE Transactions on Information Forensics and Security, 2020, 16(7): 56−69
[49]	Hu Lanqing, Kan Meina, Shan Shiguang, et al. Duplex generative adversarial network for unsupervised domain adaptation[C] //Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 1498−1507
[50]	Jourabloo A, Liu Yaojie, Liu Xiaoming. Face de-spoofing: Anti-spoofing via noise modeling[C] //Proc of the European Conf on Computer Vision. Berlin: Springer, 2018: 290−306
[51]	Yang Xiao, Luo Wenhan, Bao Linchao, et al. Face anti-spoofing: Model matters, so does data[C] //Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 3507−3516

[1]	Zhang Jing, Ju Jialiang, Ren Yonggong. Double-Generators Network for Data-Free Knowledge Distillation[J]. Journal of Computer Research and Development, 2023, 60(7): 1615-1627. DOI: 10.7544/issn1000-1239.202220024
[2]	Zhao Jingxin, Yue Xinghui, Feng Chongpeng, Zhang Jing, Li Yin, Wang Na, Ren Jiadong, Zhang Haoxing, Wu Gaofei, Zhu Xiaoyan, Zhang Yuqing. Survey of Data Privacy Security Based on General Data Protection Regulation[J]. Journal of Computer Research and Development, 2022, 59(10): 2130-2163. DOI: 10.7544/issn1000-1239.20220800
[3]	Song Xuan, Gao Yunjun, Li Yong, Guan Qingfeng, Meng Xiaofeng. Spatial Data Intelligence: Concept, Technology and Challenges[J]. Journal of Computer Research and Development, 2022, 59(2): 255-263. DOI: 10.7544/issn1000-1239.20220108
[4]	Wang Huiyong, Tang Shijie, Ding Yong, Wang Yujue, Li Jiahui. Survey on Biometrics Template Protection[J]. Journal of Computer Research and Development, 2020, 57(5): 1003-1021. DOI: 10.7544/issn1000-1239.2020.20190371
[5]	Wang Huifeng, Li Zhanhuai, Zhang Xiao, Sun Jian, Zhao Xiaonan. A Self-Adaptive Audit Method of Data Integrity in the Cloud Storage[J]. Journal of Computer Research and Development, 2017, 54(1): 172-183. DOI: 10.7544/issn1000-1239.2017.20150900
[6]	Wang Liang, Wang Weiping, Meng Dan. Privacy Preserving Data Publishing via Weighted Bayesian Networks[J]. Journal of Computer Research and Development, 2016, 53(10): 2343-2353. DOI: 10.7544/issn1000-1239.2016.20160465
[7]	Wang Jing, Huang Chuanhe, Wang Jinhai. An Access Control Mechanism with Dynamic Privilege for Cloud Storage[J]. Journal of Computer Research and Development, 2016, 53(4): 904-920. DOI: 10.7544/issn1000-1239.2016.20150158
[8]	Fu Yingxun, Luo Shengmei, Shu Jiwu. Survey of Secure Cloud Storage System and Key Technologies[J]. Journal of Computer Research and Development, 2013, 50(1): 136-145.
[9]	Hou Qinghua, Wu Yongwei, Zheng Weimin, and Yang Guangwen. A Method on Protection of User Data Privacy in Cloud Storage Platform[J]. Journal of Computer Research and Development, 2011, 48(7): 1146-1154.
[10]	Ren Wei, Ren Yi, Zhang Hui, Zhao Junge. A Secure and Efficient Data Survival Strategy in Unattended Wireless Sensor Network[J]. Journal of Computer Research and Development, 2009, 46(12): 2093-2100.

Cited By

Cited by

Periodical cited type(9)

1.	陈彩华，佘程熙，王庆阳. 可信机器学习综述. 工业工程. 2024(02): 14-26 .
2.	饶高琦，周立炜. 论语言智能的治理. 语言战略研究. 2024(03): 38-48 .
3.	穆春阳，李闯，马行，刘永鹿，杨科，刘宝成. 改进YOLOv7-tiny的轻量化大型铸件焊缝缺陷检测. 组合机床与自动化加工技术. 2024(07): 156-160 .
4.	喻继军，熊明华. 电子商务推荐系统公平性研究进展. 现代信息科技. 2023(14): 115-124 .
5.	范卓娅，孟小峰. 算法公平与公平计算. 计算机研究与发展. 2023(09): 2048-2066 . 本站查看
6.	吴雷，杜文研，林超然. 基于专利数据应用LDA和N-BEATS组合方法的技术主题预测研究. 数字图书馆论坛. 2023(11): 62-73 .
7.	古天龙，李龙，常亮，罗义琴. 公平机器学习:概念、分析与设计. 计算机学报. 2022(05): 1018-1051 .
8.	王文鑫，张健毅. 联邦学习公平性研究综述. 北京电子科技学院学报. 2022(02): 122-134 .
9.	郁建兴，刘宇轩. 社会治理中的深度学习算法公平性. 信息技术与管理应用. 2022(01): 17-27 .