Abstract
Softmax-based learning methods have shown state-of-the-art performances on large-scale face recognition tasks. In this paper, we discover an important issue of softmax-based approaches: the sample features around the corresponding class weight are similarly penalized in the training phase even though their directions are different from each other. This directional discrepancy, i.e., process discrepancy leads to performance degradation at the evaluation phase. To mitigate the issue, we propose a novel training scheme, called minimum discrepancy learning that enforces directions of intra-class sample features to be aligned toward an optimal direction by using a single learnable basis. Furthermore, the single learnable basis facilitates disentangling the so-called class-invariant vectors from sample features, such that they are effective to train under class-imbalanced datasets.
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
Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q.: Deep learning face representation by joint identification-verification. Advances in Neural Information Processing Systems (NIPS), pp. 1988–1996 (2014)
Hu, J., Lu, J., Tan, Y.P.: Discriminative deep metric learning for face verification in the wild. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1875–1882 (2014)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
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
Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: NormFace: L2 hypersphere embedding for face verification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1041–1049 (2017)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhao, K., Xu, J., Cheng, M.M.: RegularFace: deep face recognition via exclusive regularization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Feature transfer learning for face recognition with under-represented data. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Han, C., Shan, S., Kan, M., Wu, S., Chen, X.: Face recognition with contrastive convolution. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 120–135. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_8
Wang, M., Deng, W.: Deep face recognition: a survey. arXiv preprint arXiv:1804.06655 (2018)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25, 926–930 (2018)
Zheng, T., Deng, W.: Cross-pose LFW: a database for studying crosspose face recognition in unconstrained environments. Technical report (2018)
Whitelam, C., et al.: IARPA janus benchmark-b face dataset. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 592–600 (2017)
Maze, B., et al.: IARPA janus benchmark-C: face dataset and protocol. In: International Conference on Biometrics (ICB), pp. 158–165 (2018)
Cheng, Z., Zhu, X., Gong, S.: Surveillance face recognition challenge. arXiv preprint arXiv:1804.09691 (2018)
Chen, B., Deng, W., Shen, H.: Virtual class enhanced discriminative embedding learning. In: Advances in Neural Information Processing Systems (NIPS), pp. 1942–1952 (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (ICLR), pp. 6438–6447 (2018)
Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: The International Conference on Machine Learning (ICML), pp. 6438–6447 (2019)
Kim, I., Kim, K., Kim, J., Choi, C.: Deep speaker representation using orthogonal decomposition and recombination for speaker verification. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6129–6130 (2019). https://doi.org/10.1109/ICASSP.2019.8683332
Jang, E., Gu, S., Poole, B.: Categorical reparametrization with gumble-softmax. In: International Conference on Learning Representations (ICLR) (2017)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks . In: International Conference on Machine Learning (ICML), pp. 1321–1330 (2017)
Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. In: International Conference on Learning Representations (ICLR) (2017)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Ranjan, R., et al: Crystal loss and quality pooling for unconstrained face verification and recognition. arXiv preprint arXiv:1804.01159 (2018)
Zheng, Y., Pal, D.K., Savvides, M.: Ring loss: convex feature normalization for face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: VGGFace2: a dataset for recognising faces across pose and age. In: The IEEE Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 67–74 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Dong, Y., Zhen Lei, S.L., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)
Sengupta, S., Chen, J.C., Castillo, C., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: The IEEE Winter Conference on Applications of Computer Vision (WACV) (2016)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23, 1499–1503 (2016)
Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical Report 07–49, University of Massachusetts, Amhertst (2007)
Zheng, T., Deng, W., Hu, J.: Cross-age LFW: a database for studying cross-age face recognition in unconstrained environments. arXiv:1708.08197 (2017)
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database. In: The IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 51–59 (2017)
Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The megaface benchmark: 1 million faces for recognition at scale. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4873–4882 (2016)
Ng, H.W., Winkler, S.: A data-driven approach to cleaning large face datasets. In: IEEE International Conference on Image Processing (ICIP), pp. 343–347 (2014)
Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2892–2900 (2015)
Wang, Y., et al.: Orthogonal deep features decomposition for age-invariant face recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 764–779. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_45
Shi, Y., Jain, A.K.: Probabilistic face embeddings. In: The IEEE International Conference on Computer Vision (ICCV) (2019)
Liu, H., Zhu, X., Lei, Z., Li, S.Z.: AdaptiveFace: adaptive margin and sampling for face recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_6
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted Gaussian mixture models. Digit. Signal Proc. 10, 19–41 (2000)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, I. et al. (2021). DiscFace: Minimum Discrepancy Learning for Deep Face Recognition. In: Ishikawa, H., Liu, CL., Pajdla, T., Shi, J. (eds) Computer Vision – ACCV 2020. ACCV 2020. Lecture Notes in Computer Science(), vol 12626. Springer, Cham. https://doi.org/10.1007/978-3-030-69541-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-69541-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69540-8
Online ISBN: 978-3-030-69541-5
eBook Packages: Computer ScienceComputer Science (R0)