Abstract
Face recognition has achieved great progress because of the advancement of deep convolutional neural networks (CNNs) techniques. The Softmax loss is one of the most popular loss function for deep learning models. In many situations, face images are captured in the unconstrained environments with changing poses and illuminations, making face recognition very challenging because of the dramatic appearance variations. The models trained with the Softmax loss may fail to extract discriminative information for the face images with extreme illumination or pose conditions. Recently, Cosface has been proven effective for improving the generalization ability of the Softmax loss. Derived from Cosface, we propose a novel method named Penalty Cosface to address the unconstrained face recognition challenges and learn discriminative features. Specifically, we design a variant of Cosface that remove radial variations by penalizing \(\ell _2\)-normalized constraints of the features and weights. Therefore, the discriminative ability of the Penalty Cosface is guaranteed by the large margin of the Cosface, and the penalty term is beneficial to simplifying the gradient calculations. Experimental results show that the Penalty Cosface improves the discriminative power of deep networks and outperforms the other variants of Softmax loss.
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
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: a dataset for recognising faces across pose and age. In: Proceedings of the IEEE International Conference on Automatic Face & Gesture Recognition, pp. 67–74 (2018)
Chen, S., Liu, Y., Gao, X., Han, Z.: MobileFaceNets: efficient CNNs for accurate real-time face verification on mobile devices. In: Zhou, J., et al. (eds.) CCBR 2018. LNCS, vol. 10996, pp. 428–438. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-97909-0_46
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, G.B., Ramesh, 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, Amherst (2007)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations. vol. abs/1412.6980 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017)
Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: Proceedings of the International Conference on Machine Learning, pp. 507–516 (2016)
Masi, I., Wu, Y., Hassner, T., Natarajan, P.: Deep face recognition: a survey. In: Proceedings of the SIBGRAPI Conference on Graphics, Patterns and Images, pp. 471–478 (2018)
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: Agedb: the first manually collected, in-the-wild age database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 51–59 (2017)
Nocedal, J., Wright, S.: Numerical Optimization. Springer, New York (2006). https://doi.org/10.1007/978-0-387-40065-5
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Sengupta, S., Chen, J.C., Castillo, C., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1–9 (2016)
Shan, C., Gong, S., McOwan, P.W.: Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis. Comput. 27(6), 803–816 (2009)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2015)
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems, pp. 1988–1996 (2014)
Sun, Y., Liang, D., Wang, X., Tang, X.: Deepid3: face recognition with very deep neural networks. CoRR abs/1502.00873 (2015)
Taigman, Y., Yang, M., Ranzato, M., 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)
Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926–930 (2018)
Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265–5274 (2018)
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
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. CoRR abs/1411.7923 (2014)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 915–928 (2007)
Acknowledgment
This project was supported by the Key Areas Research and Development Program of Guangdong Province (2019B010155003) and NSFC (61876104, 61902444).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, S., Tang, J., Feng, Z., Lai, J. (2020). Deep Face Recognition Based on Penalty Cosface. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)