Advertisement

MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

  • Sheng Chen
  • Yang Liu
  • Xiang Gao
  • Zhen Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

We present a class of extremely efficient CNN models, MobileFaceNets, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. We first make a simple analysis on the weakness of common mobile networks for face verification. The weakness has been well overcome by our specifically designed MobileFaceNets. Under the same experimental conditions, our MobileFaceNets achieve significantly superior accuracy as well as more than 2 times actual speedup over MobileNetV2. After trained by ArcFace loss on the refined MS-Celeb-1 M, our single MobileFaceNet of 4.0 MB size achieves 99.55% accuracy on LFW and 92.59% TAR@FAR1e-6 on MegaFace, which is even comparable to state-of-the-art big CNN models of hundreds MB size. The fastest one of MobileFaceNets has an actual inference time of 18 ms on a mobile phone. For face verification, MobileFaceNets achieve significantly improved efficiency over previous state-of-the-art mobile CNNs.

Keywords

Mobile network Face verification Face recognition Convolutional neural network Deep learning 

Notes

Acknowledgements

We thank Jia Guo for helpful discussion, and thank Yang Wang, Lian Li, Licang Qin, Yan Gao, Hua Chen, and Min Zhao for application development.

References

  1. 1.
    Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs/1704.04861 (2017)Google Scholar
  2. 2.
    Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. CoRR, abs/1707.01083 (2017)Google Scholar
  3. 3.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted Residuals and Linear Bottlenecks. CoRR, abs/1801.04381 (2018)Google Scholar
  4. 4.
    Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: Ms-celeb-1 m: A dataset and benchmark for large-scale face recognition, arXiv preprint (2016). arXiv:1607.08221
  5. 5.
    Deng, J., Guo, J., Zafeiriou, S.: ArcFace: Additive Angular Margin Loss for Deep Face Recognition. arXiv preprint (2018). arXiv:1801.07698
  6. 6.
    Huang, G.B., Ramesh, M., Berg, T., et al.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments (2007)Google Scholar
  7. 7.
    Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The megaface benchmark: 1 million faces for recognition at scale. In: CVPR (2016)Google Scholar
  8. 8.
    Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: The first manually collected in-the-wild age database. In: CVPRW (2017)Google Scholar
  9. 9.
    Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and 0.5 MB model size, arXiv preprint (2016). arXiv:1602.07360
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  11. 11.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR. IEEE (2009)Google Scholar
  12. 12.
    Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition, arXiv preprint (2017). arXiv:1707.07012
  14. 14.
    Wu, X., He, R., Sun, Z., Tan, T.: A light cnn for deep face representation with noisy labels, arXiv preprint (2016). arXiv:1511.02683
  15. 15.
    Wu, B., Wan, A., Yue, X., Jin, P., Zhao, S., Golmant, N., et al.: Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions, arXiv preprint (2017). arXiv:1711.08141
  16. 16.
    Hinton, G. E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531
  17. 17.
    Luo, P., Zhu, Z., Liu, Z., Wang, X., Tang, X., Luo, P., et al.: Face Model Compression by Distilling Knowledge from Neurons. In: AAAI (2016)Google Scholar
  18. 18.
    Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015)Google Scholar
  19. 19.
    Long, J., Zhang, N., Darrell, T.: Do convnets learn correspondence? Adv. Neural. Inf. Process. Syst. 2, 1601–1609 (2014)Google Scholar
  20. 20.
    Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: CVPR (2017)Google Scholar
  21. 21.
    Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Proc. Lett. 25(7), 926–930 (2018)CrossRefGoogle Scholar
  22. 22.
    Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., et al.: CosFace: Large Margin Cosine Loss for Deep Face Recognition (2018). arXiv:1801.0941
  23. 23.
    Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Proc. Lett. 23(10), 1499–1503 (2016)CrossRefGoogle Scholar
  24. 24.
    Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: NIPS (2016)Google Scholar
  25. 25.
    Chollet, F.: Xception: Deep learning with depthwise separable convolutions, arXiv preprint (2016). arXiv:1610.02357
  26. 26.
    Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch, arXiv preprint (2014). arXiv:1411.7923
  27. 27.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: CVPR (2015)Google Scholar
  28. 28.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)Google Scholar
  29. 29.
    Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., et al.: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference, arXiv preprint (2017). arXiv:1712.05877
  30. 30.
    NCNN: a high-performance neural network inference framework optimized for the mobile platform, Apr 20 2018. https://github.com/Tencent/ncnn
  31. 31.
    Taigman, Y., Yang, M., Ranzato, M., et al.: DeepFace: closing the gap to human-level performance in face verification. In: CVPR (2014)Google Scholar
  32. 32.
    Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015)Google Scholar
  33. 33.
    Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: Computer Vision and Pattern Recognition, pp. 2892–2900 (2015)Google Scholar
  34. 34.
    Wen, Y., Zhang, K., Li, Z., Qiao, Y.: 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_31CrossRefGoogle Scholar
  35. 35.
    Deng, W., Chen, B., Fang, Y., Hu, J.: Deep Correlation Feature Learning for Face Verification in the Wild. IEEE Signal Proc. Lett. 24(12), 1877–1881 (2017)CrossRefGoogle Scholar
  36. 36.
    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)Google Scholar
  37. 37.
    Han, S., Mao, H., Dally, W.J.: Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding, CoRR, abs/1510.00149 (2015)Google Scholar
  38. 38.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Computer and Information TechnologyBeijing Jiaotong UniversityBeijingChina
  2. 2.Research Institute, Watchdata Inc.BeijingChina

Personalised recommendations