Abstract
Compared with traditional 3D face recognition tasks using high precision 3D face scans, 3D face recognition based on low-quality data captured by consumer depth cameras is more practicable for real-world applications. However, it is also more challenging to deal with the variations of facial expressions, poses, occlusions, data noises, scanning distance, and so on. In this paper, we propose a novel robust low-quality 3D face recognition method based on Facial Adversarial Sample Augmentation, namely FASA-3DFR. It consists of two modules, namely facial adversarial sample generation, and facial adversarial sample training. For the first module, to enlarge the diversity of facial adversarial samples and boost the robustness of 3DFR, we propose to utilize the Kullback-Leibler divergence to maximize the distribution distance between the original and adversarial facial samples. For the second module, a distribution alignment loss is designed to make the distribution of facial adversarial samples gradually close to the one of the original facial samples, and the common and valuable information from both distributions can be effectively extracted. Extensive experiments conducted on the CAS-AIR-3D Face database show the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhou, S., Xiao, S.: 3D face recognition: a survey. HCIS 8(1), 1–27 (2018)
Rebuffi, S.-A., et al.: Data augmentation can improve robustness. In: Advances in Neural Information Processing Systems, vol. 34, pp. 29935–29948 (2021)
Schlett, T., Rathgeb, C., Busch, C.: Deep learning-based single image face depth data enhancement. Comput. Vis. Image Underst. 210, 103247 (2021)
Yu, C., et al.: Meta-learning-based adversarial training for deep 3D face recognition on point clouds. Pattern Recogn. 134, 109065 (2023)
Tang, S., et al.: RobustART: benchmarking robustness on architecture design and training techniques. arXiv preprint arXiv:2109.05211 (2021)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Proceedings of ICLR (2018)
Sinha, A., Namkoong, H., Volpi, R., Duchi, J.: Certifying some distributional robustness with principled adversarial training. In: Proceedings of ICLR (2018)
Kang, D., Sun, Y., et al.: Transfer of adversarial robustness between perturbation types. arXiv preprint arXiv:1905.01034 (2019)
Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A.L., Le, Q.V.: Adversarial examples improve image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 819–828 (2020)
Zhang, J., Huang, D., Wang, Y., Sun, J.: Lock3DFace: a large-scale database of low-cost kinect 3D faces. In: International Conference on Biometrics, pp. 1–8 (2016)
Li, Q., Dong, X., Wang, W., Shan, C.: CAS-AIR-3D Face: a low-quality, multi-modal and multi-pose 3D face database. In: IEEE International Joint Conference on Biometrics, pp. 1–8 (2021)
Cui, J., Zhang, H., et al.: Improving 2D face recognition via discriminative face depth estimation. In: International Conference on Biometrics, pp. 140–147 (2018)
Mu, G., Huang, D., et al.: Led3D: a lightweight and efficient deep approach to recognizing low-quality 3D faces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5773–5782 (2019)
Lin, S., Jiang, C., Liu, F., Shen, L.: High quality facial data synthesis and fusion for 3D low-quality face recognition. In: IEEE International Joint Conference on Biometrics, pp. 1–8 (2021)
Zhang, Z., Yu, C., Xu, S., Li, H.: Learning flexibly distributional representation for low-quality 3D face recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3465–3473 (2021)
Jiang, C., Lin, S., Chen, W., Liu, F., Shen, L.: PointFace: point set based feature learning for 3D face recognition. In: IEEE International Joint Conference on Biometrics, pp. 1–8 (2021)
Zhao, P., Ming, Y., Meng, X., Yu, H.: LMFNet: a lightweight multiscale fusion network with hierarchical structure for low-quality 3-D face recognition. IEEE Trans. Hum.-Mach. Syst. 53(1), 239–52 (2022)
Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: RetinaFace: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5203–5212 (2020)
Guo, X., et al.: PFLD: a practical facial landmark detector. arXiv preprint arXiv:1902.10859 (2019)
Wu, X., He, R., et al.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. 13(11), 2884–2896 (2018)
Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Deng, J., Guo, J., et al.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China (Grant No. 61976173) and the Shaanxi Fundamental Science Research Project for Mathematics and Physics (Grant No. 22JSY011).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sun, F., Yu, C., Li, H. (2023). Facial Adversarial Sample Augmentation for Robust Low-Quality 3D Face Recognition. In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_16
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)