Additive Parameter for Deep Face Recognition

Abstract

The performance of feature learning for deep convolutional neural networks (DCNNs) is increasing promptly with significant improvement in numerous applications. Recent studies on loss functions clearly describing that better normalization is helpful for improving the performance of face recognition (FR). Several methods based on different loss functions have been proposed for FR to obtain discriminative features. In this paper, we propose an additive parameter depending on multiplicative angular margin to improve the discriminative power of feature embedding that can be easily implemented. In additive parameter approach, an automatic adjustment of the seedling element as the result of angular marginal seed is offered in a particular way for the angular softmax to learn angularly discriminative features. We train the model on publically available dataset CASIA-WebFace, and our experiments on famous benchmarks YouTube Faces (YTF) and labeled face in the wild (LFW) achieve better performance than the various state-of-the-art approaches.

Keywords

Additive parameter / Angular margin / Deep convolutional neural networks / Face recognition / Softmax loss

References

[1] Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: a dataset for recognizing faces across pose and age. In: 13th IEEE International Conference on Automatic Face and Gesture Recognition, FG, pp. 67–74 (2018)

[2] Deng, J., Guo, J., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition (2018). arXiv preprint arXiv:1801.07698

[3] He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

[4] Hoffer Elad, Ailon Nir. Deep Metric Learning Using Triplet Network. Similarity-Based Pattern Recognition. 2015 Cham: Springer International Publishing. 84-92

[5] Huang, G.B., Learned-Miller, E.: Labeled faces in the wild: updates and new reporting procedures. Dept. Comput. Sci., Univ. Massachusetts Amherst, Amherst, MA, USA, Tech. Rep, pp. 14-003 (2014)

[6] Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In Technical Report 07-49, University of Massachusetts, Amherst (2017)

[7] Li, S.Z., Yi, D., Lei, Z., Liao, S.: The casia nir-vis 2.0 face database. (2013) In: CVPR Workshops, pp. 348–353. IEEE (2013)

[8] Liu, Y., Li, H., Wang, X.: Rethinking feature discrimination and polymerization for large-scale recognition (2017). arXiv preprint arXiv:1710.00870

[9] Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: ICML, pp. 507–516 (2016)

[10] Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embed-ding for face recognition. In: CVPR (2017)

[11] Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: BMVC (2015)

[12] Ranjan, R., Castillo, C.D., Chellappa, R.: L2-constrained softmax loss for discriminative face verification (2017). arXiv preprint arXiv:1703.09507

[13] Ranjan R, Sankaranarayanan S, Bansal A, Bodla N, Chen JC, Patel VM, Castillo CD, Chellappa R. Deep learning for understanding faces: machines may be just as good, or better, than humans. IEEE Signal Process. Mag.. 2018, 35 1 66-83

[14] Schro, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015)

[15] Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)

[16] Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: NIPS (2014)

[17] Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: CVPR (2015)

[18] Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human level performance in face verification. In: CVPR (2014)

[19] Wang Feng, Cheng Jian, Liu Weiyang, Liu Haijun. Additive Margin Softmax for Face Verification. IEEE Signal Processing Letters. 2018, 25 7 926-930

[20] 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. ACM (2017)

[21] Wang, H., Wang, Y., Zhou, Z., Ji, X., Li, Z., Gong, D., Zhou, J., Liu, W.: CosFace: large margin cosine loss for deep face recognition. In: CVPR (2018)

[22] Wen Yandong, Zhang Kaipeng, Li Zhifeng, Qiao Yu. A Discriminative Feature Learning Approach for Deep Face Recognition. Computer Vision – ECCV 2016. 2016 Cham: Springer International Publishing. 499-515

[23] Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: CVPR (2011)

[24] Zhang Kaipeng, Zhang Zhanpeng, Li Zhifeng, Qiao Yu. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Processing Letters. 2016, 23 10 1499-1503