Skip to main content

2018 | OriginalPaper | Buchkapitel

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

verfasst von : Sheng Chen, Yang Liu, Xiang Gao, Zhen Han

Erschienen in: Biometric Recognition

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

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.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat 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) 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)
2.
Zurück zum Zitat Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. CoRR, abs/1707.01083 (2017) Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. CoRR, abs/1707.01083 (2017)
3.
Zurück zum Zitat Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted Residuals and Linear Bottlenecks. CoRR, abs/1801.04381 (2018) Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted Residuals and Linear Bottlenecks. CoRR, abs/1801.04381 (2018)
4.
Zurück zum Zitat 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 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.
Zurück zum Zitat Deng, J., Guo, J., Zafeiriou, S.: ArcFace: Additive Angular Margin Loss for Deep Face Recognition. arXiv preprint (2018). arXiv:1801.07698 Deng, J., Guo, J., Zafeiriou, S.: ArcFace: Additive Angular Margin Loss for Deep Face Recognition. arXiv preprint (2018). arXiv:​1801.​07698
6.
Zurück zum Zitat Huang, G.B., Ramesh, M., Berg, T., et al.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments (2007) Huang, G.B., Ramesh, M., Berg, T., et al.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments (2007)
7.
Zurück zum Zitat Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The megaface benchmark: 1 million faces for recognition at scale. In: CVPR (2016) Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The megaface benchmark: 1 million faces for recognition at scale. In: CVPR (2016)
8.
Zurück zum Zitat 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) 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)
9.
Zurück zum Zitat 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 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.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)
11.
Zurück zum Zitat 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) 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)
12.
Zurück zum Zitat Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)MathSciNetCrossRef Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)MathSciNetCrossRef
13.
Zurück zum Zitat Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition, arXiv preprint (2017). arXiv:1707.07012 Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition, arXiv preprint (2017). arXiv:​1707.​07012
14.
Zurück zum Zitat Wu, X., He, R., Sun, Z., Tan, T.: A light cnn for deep face representation with noisy labels, arXiv preprint (2016). arXiv:1511.02683 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.
Zurück zum Zitat 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 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
17.
Zurück zum Zitat 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) 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)
18.
Zurück zum Zitat Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015) Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015)
19.
Zurück zum Zitat Long, J., Zhang, N., Darrell, T.: Do convnets learn correspondence? Adv. Neural. Inf. Process. Syst. 2, 1601–1609 (2014) Long, J., Zhang, N., Darrell, T.: Do convnets learn correspondence? Adv. Neural. Inf. Process. Syst. 2, 1601–1609 (2014)
20.
Zurück zum Zitat Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: CVPR (2017) Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: CVPR (2017)
21.
Zurück zum Zitat Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Proc. Lett. 25(7), 926–930 (2018)CrossRef Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Proc. Lett. 25(7), 926–930 (2018)CrossRef
22.
Zurück zum Zitat 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 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.
Zurück zum Zitat 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)CrossRef 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)CrossRef
24.
Zurück zum Zitat Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: NIPS (2016) Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: NIPS (2016)
26.
27.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: CVPR (2015) He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: CVPR (2015)
28.
Zurück zum Zitat Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015) Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)
29.
Zurück zum Zitat 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 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
31.
Zurück zum Zitat Taigman, Y., Yang, M., Ranzato, M., et al.: DeepFace: closing the gap to human-level performance in face verification. In: CVPR (2014) Taigman, Y., Yang, M., Ranzato, M., et al.: DeepFace: closing the gap to human-level performance in face verification. In: CVPR (2014)
32.
Zurück zum Zitat Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015) Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015)
33.
Zurück zum Zitat 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) 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)
35.
Zurück zum Zitat 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)CrossRef 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)CrossRef
36.
Zurück zum Zitat 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) 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)
37.
Zurück zum Zitat 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) 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)
38.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Metadaten
Titel
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
verfasst von
Sheng Chen
Yang Liu
Xiang Gao
Zhen Han
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-97909-0_46

Premium Partner