Abstract
Large facial variations are the main challenge in face recognition. To this end, previous variation-specific methods make full use of task-related prior to design special network losses, which are typically not general among different tasks and scenarios. In contrast, the existing generic methods focus on improving the feature discriminability to minimize the intra-class distance while maximizing the inter-class distance, which perform well on easy samples but fail on hard samples. To improve the performance on hard samples, we propose a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples, which is simple, effective and generic for various types of facial variations. Specifically, we first adopt state-of-the-art classifiers such as Arcface to construct two similarity distributions: a teacher distribution from easy samples and a student distribution from hard samples. Then, we propose a novel distribution-driven loss to constrain the student distribution to approximate the teacher distribution, which thus leads to smaller overlap between the positive and negative pairs in the student distribution. We have conducted extensive experiments on both generic large-scale face benchmarks and benchmarks with diverse variations on race, resolution and pose. The quantitative results demonstrate the superiority of our method over strong baselines, e.g., Arcface and Cosface. Code will be available at https://github.com/HuangYG123/DDL.
Y. Huang and P. Shen—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/. software available from tensorflow.org
Cao, K., Rong, Y., Li, C., Tang, X., Change Loy, C.: Pose-robust face recognition via deep residual equivariant mapping. In: CVPR, pp. 5187–5196 (2018)
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: a dataset for recognising faces across pose and age. In: FG, pp. 67–74. IEEE (2018)
Chen, Y., Tai, Y., Liu, X., Shen, C., Yang, J.: FSRNet: end-to-end learning face super-resolution with facial priors. In: CVPR, pp. 2492–2501 (2018)
Deng, J., Cheng, S., Xue, N., Zhou, Y., Zafeiriou, S.: UV-GAN: adversarial facial UV map completion for pose-invariant face recognition. In: CVPR, pp. 7093–7102 (2018)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: CVPR, pp. 4690–4699 (2019)
Deng, J., Zhou, Y., Zafeiriou, S.: Marginal loss for deep face recognition. In: CVPR Workshops, pp. 60–68 (2017)
Gong, S., Liu, X., Jain, A.: Jointly de-biasing face recognition and demographic attribute estimation. In: ECCV (2020)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)
Grgic, M., Delac, K., Grgic, S.: SCface-surveillance cameras face database. Multimedia Tools Appli. 51(3), 863–879 (2011). https://doi.org/10.1007/s11042-009-0417-2
Hennings-Yeomans, P.H., Baker, S., Kumar, B.V.: Simultaneous super-resolution and feature extraction for recognition of low-resolution faces. In: CVPR, pp. 1–8. IEEE (2008)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Workshop (2014)
Huang, Y., et al.: CurricularFace: adaptive curriculum learning loss for deep face recognition. In: CVPR (2020)
Huang, Z., Wang, N.: Like what you like: knowledge distill via neuron selectivity transfer (2017). arXiv:1707.01219v2
Huang, Z., et al.: A benchmark and comparative study of video-based face recognition on cox face database. IEEE Trans. Image Process. 24(12), 5967–5981 (2015)
Lei, Z., Ahonen, T., Pietikäinen, M., Li, S.Z.: Local frequency descriptor for low-resolution face recognition. In: FG, pp. 161–166. IEEE (2011)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2980–2988 (2017)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: CVPR, pp. 212–220 (2017)
Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: ICML, vol. 2, p. 7 (2016)
Lu, Z., Jiang, X., Kot, A.: Deep coupled resnet for low-resolution face recognition. IEEE Sig. Process. Lett. 25(4), 526–530 (2018)
Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)
Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3967–3976 (2019)
Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015)
Peng, X., Yu, X., Sohn, K., Metaxas, D.N., Chandraker, M.: Reconstruction-based disentanglement for pose-invariant face recognition. In: ICCV, pp. 1623–1632 (2017)
Ruiz, N., Chong, E., Rehg, J.M.: Fine-grained head pose estimation without keypoints. In: CVPR Workshops, pp. 2074–2083 (2018)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815–823 (2015)
Shekhar, S., Patel, V.M., Chellappa, R.: Synthesis-based recognition of low resolution faces. In: IJCB, pp. 1–6. IEEE (2011)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR, pp. 761–769 (2016)
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: NIPS, pp. 1988–1996 (2014)
Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: CVPR, pp. 1891–1898 (2014)
Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: CVPR, pp. 3147–3155 (2017)
Tai, Y., Yang, J., Liu, X., Xu, C.: Memnet: a persistent memory network for image restoration. In: ICCV, pp. 4539–4547 (2017)
Tai, Y., Yang, J., Zhang, Y., Luo, L., Qian, J., Chen, Y.: Face recognition with pose variations and misalignment via orthogonal procrustes regression. IEEE Trans. Image Process. 25(6), 2673–2683 (2016)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: CVPR, pp. 1701–1708 (2014)
Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR, pp. 1415–1424 (2017)
Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1365–1374 (2019)
Ustinova, E., Lempitsky, V.: Learning deep embeddings with histogram loss. In: NIPS, pp. 4170–4178 (2016)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Sig. Process. Lett. 25(7), 926–930 (2018)
Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: Normface: L2 hypersphere embedding for face verification. In: ACMMM, pp. 1041–1049. ACM (2017)
Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: CVPR, pp. 5265–5274 (2018)
Wang, X., Wang, S., Wang, J., Shi, H., Mei, T.: Co-mining: deep face recognition with noisy labels. In: ICCV, pp. 9358–9367 (2019)
Wang, X., Wang, S., Zhang, S., Fu, T., Shi, H., Mei, T.: Support vector guided softmax loss for face recognition (2018). arXiv:1812.11317
Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31
Xie, W., Shen, L., Zisserman, A.: Comparator networks. In: ECCV, pp. 782–797 (2018)
Xie, W., Zisserman, A.: Multicolumn networks for face recognition. In: BMVC (2018)
Yang, F., Yang, W., Gao, R., Liao, Q.: Discriminative multidimensional scaling for low-resolution face recognition. IEEE Sig. Process. Lett. 25(3), 388–392 (2017)
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch (2014).arXiv:1411.7923
Yin, X., Liu, X.: Multi-task convolutional neural network for pose-invariant face recognition. IEEE Trans. Image Process. 27(2), 964–975 (2017)
Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Towards large-pose face frontalization in the wild. In: ICCV, pp. 3990–3999 (2017)
Zhang, K., et al.: Super-identity convolutional neural network for face hallucination. In: ECCV, pp. 183–198 (2018)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sig. Process. Lett. 23(10), 1499–1503 (2016)
Zhang, X., Fang, Z., Wen, Y., Li, Z., Qiao, Y.: Range loss for deep face recognition with long-tailed training data. In: ICCV, pp. 5409–5418 (2017)
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: CVPR, pp. 4320–4328 (2018)
Zhao, J., et al.: 3D-aided deep pose-invariant face recognition. In: IJCAI, vol. 2, p. 11 (2018)
Zou, W.W., Yuen, P.C.: Very low resolution face recognition problem. IEEE Trans. Image Process. 21(1), 327–340 (2011)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, Y. et al. (2020). Improving Face Recognition from Hard Samples via Distribution Distillation Loss. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12375. Springer, Cham. https://doi.org/10.1007/978-3-030-58577-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-58577-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58576-1
Online ISBN: 978-3-030-58577-8
eBook Packages: Computer ScienceComputer Science (R0)