Advertisement

CNN-Based Age Classification via Transfer Learning

  • Jian Lin
  • Tianyue Zheng
  • Yanbing Liao
  • Weihong Deng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10559)

Abstract

Age estimation has always hit people’s eyes. While most previous works have focused on constrained images taken under lab condition, which is far from real-world age estimation. The benchmark we used in this paper is the unconstrained Adience [3], which is believed to better reflect the traits of age in the wild condition. In this paper, we adapted contrastive loss to fine-tune the pre-trained VGG-16 over FG-NET to get a better start point and proposed AvgOut-FC Layer to enhance the performance of the models over Audience. We have achieved better results over the Adience benchmark than previous works, which demonstrated the effectiveness of our methods.

Keywords

Unconstrained age estimation Convolutional Neural Network Transform learning 

Notes

Acknowledgements

This work was partially supported by Beijing Nova Program under Grant No. Z161100004916088, the National Natural Science Foundation of China (Project 61573068, 61471048, and 61375031), and the Fundamental Research Funds for the Central Universities under Grant No. 2014ZD03-01.

References

  1. 1.
    Goodfellow, I.J., Wardefarley, D., Mirza, M., et al.: Maxout networks. Comput. Sci. 1319–1327 (2013)Google Scholar
  2. 2.
    Levi, G., Hassner, T.: Age and gender classification using convolutional neural networks. In: IEEE Conference on CVPR Workshops (2015)Google Scholar
  3. 3.
    Eidinger, E., Enbar, R., Hassner, T.: Age and gender estimation of unfiltered faces. Trans. Inform. Forensics Secur. 9(12), 1, 2, 5, 6 (2014)Google Scholar
  4. 4.
    Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1. IEEE (2005)Google Scholar
  5. 5.
    Ozbulak, G., Aytar, Y., Ekenel, H.K.: How transferable are CNN-based features for age and gender classification? In: International Conference of the Biometrics Special Interest Group, pp. 1–6 (2016)Google Scholar
  6. 6.
    Lanitis, A.: The FG-NET Aging Database (2002). www-prima.inrialpes.fr/FGnet/html/benchmarks.html
  7. 7.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. S. 1097–1105 (2012)Google Scholar
  8. 8.
    Yosinski, J., et al.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems (2014)Google Scholar
  9. 9.
    Oquab, M., et al.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR. IEEE (2014)Google Scholar
  10. 10.
    Fu, Y., Guo, G., Huang, T.: Age synthesis and estimation via faces: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 32(11), 1955–1976 (2010)CrossRefGoogle Scholar
  11. 11.
    Han, H., Otto, C., Liu, X., Jain, A.: Demographic estimation from face images: human vs. machine performance. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 37(6), 1148–1161 (2015)CrossRefGoogle Scholar
  12. 12.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: International Conference on Multimedia, pp. S. 675–678. ACM (2014)Google Scholar
  13. 13.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRRabs/1409.1556 (2014)Google Scholar
  15. 15.
    Luo, P., Wang, X., Tang, X.: Hierarchical face parsing via deep learning. In: Proceedings of Conference on Computer Vision Pattern Recognition, vol. 3, pp. 2480–2487. IEEE (2012)Google Scholar
  16. 16.
    Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of Conference on Computer Vision Pattern Recognition, vol. 3, pp. 1653–1660. IEEE (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jian Lin
    • 1
  • Tianyue Zheng
    • 1
  • Yanbing Liao
    • 1
  • Weihong Deng
    • 1
  1. 1.Beijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations