Abstract
In this work we have investigated face verification based on deep representations from Convolutional Neural Networks (CNNs) to find an accurate and compact face descriptor trained only on a restricted amount of face image data. Transfer learning by fine-tuning CNNs pre-trained on large-scale object recognition has been shown to be a suitable approach to counter a limited amount of target domain data. Using model compression we reduced the model complexity without significant loss in accuracy and made the feature extraction more feasible for real-time use and deployment on embedded systems and mobile devices. The compression resulted in a 9-fold reduction in number of parameters and a 5-fold speed-up in the average feature extraction time running on a desktop CPU. With continued training of the compressed model using a Siamese Network setup, it outperformed the larger model.
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
Notes
- 1.
FaceScrub and MSRA-CFW were downloaded from individual URLs and many images failed to download or were corrupt. For MSRA-CFW we applied a haar-cascade face detector on the downloaded images and created weak annotations.
References
Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: From generic to specific deep representations for visual recognition. CoRR abs/1406.5774 (2014). http://arxiv.org/abs/1406.5774
Ba, L.J., Caurana, R.: Do deep nets really need to be deep? CoRR abs/1312.6184 (2013). http://arxiv.org/abs/1312.6184
Bell, S., Bala, K.: Learning visual similarity for product design with convolutional neural networks. ACM Trans. Graph. 34(4), 98:1–98:10 (2015). http://doi.acm.org/10.1145/2766959
Bucila, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, 20–23 Aug 2006, pp. 535–541 (2006)
Chen, D., Cao, X., Wang, L., Wen, F., Sun, J.: Bayesian face revisited: a joint formulation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 566–579. Springer, Heidelberg (2012). http://dx.doi.org/10.1007/978-3-642-33712-3_41
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 539–546 (2005)
Grundström, J.: Face verification and open-set identification for real-time video applications (2015). Student Paper
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735–1742 (2006)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). http://arxiv.org/abs/1503.02531
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, October 2007
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding (2014). arXiv preprint arXiv:1408.5093
Karayev, S., Hertzmann, A., Winnemoeller, H., Agarwala, A., Darrell, T.: Recognizing image style. CoRR abs/1311.3715 (2013). http://arxiv.org/abs/1311.3715
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
Luo, P., Zhu, Z., Liu, Z., Wang, X., Tang, X.: Face model compression by distilling knowledge from neurons (2016). http://personal.ie.cuhk.edu.hk/~pluo/pdf/aaai16-face-model-compression.pdf
Ng, H., Winkler, S.: A data-driven approach to cleaning large face datasets. In: ICIP14, pp. 343–347 (2014)
Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: British Machine Vision Conference (2015)
Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. CoRR abs/1403.6382 (2014). http://arxiv.org/abs/1403.6382
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. CoRR abs/1503.03832 (2015). http://arxiv.org/abs/1503.03832
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations (ICLR 2014). CBLS, April 2014. http://openreview.net/document/d332e77d-459a-4af8-b3ed-55ba
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014). http://arxiv.org/abs/1409.1556
Sun, Y., Wang, X., Tang, X.: Deep Learning Face Representation by Joint Identification-Verification. Ph.D. thesis, arXiv (2014). http://arxiv.org/abs/1406.4773
Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Computer Vision and Pattern Recognition, pp. 1891–1898. IEEE (2014)
Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. CoRR abs/1412.1265 (2014). http://arxiv.org/abs/1412.1265
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Zhang, X., Zhang, L., Wang, X.J., Shum, H.Y.: Finding celebrities in billions of web images. IEEE Trans. Multimedia 14(4), 995–1007 (2012)
Zhou, E., Cao, Z., Yin, Q.: Naive-deep face recognition: touching the limit of LFW benchmark or not? CoRR abs/1501.04690 (2015). http://arxiv.org/abs/1501.04690
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Grundström, J., Chen, J., Ljungqvist, M.G., Åström, K. (2016). Transferring and Compressing Convolutional Neural Networks for Face Representations. In: Campilho, A., Karray, F. (eds) Image Analysis and Recognition. ICIAR 2016. Lecture Notes in Computer Science(), vol 9730. Springer, Cham. https://doi.org/10.1007/978-3-319-41501-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-41501-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41500-0
Online ISBN: 978-3-319-41501-7
eBook Packages: Computer ScienceComputer Science (R0)