Channel-level acceleration of deep face representations

IEEE Access

Volumn 3, Issue , 2015, Pages 2163-2175

  Polyak, Adam ^a   Wolf, Lior ^a  

^a TEL AVIV UNIVERSITY   (Israel)

Author keywords

Face recognition; Neural network compression

Indexed keywords

NETWORK ARCHITECTURE; OBJECT RECOGNITION;

ACTIVE CHANNELS; CHANNEL-LEVEL; COMPRESSION METHODS; DEEP LEARNING; FACE REPRESENTATIONS; HARDWARE RESOURCES; NETWORK COMPRESSION; NOVEL METHODS;

FACE RECOGNITION;

EID: 84961358915     PISSN: None     EISSN: 21693536     Source Type: Journal    
DOI: 10.1109/ACCESS.2015.2494536     Document Type: Article

References (38)

1. Y. LeCun et al., "Backpropagation applied to handwritten zip code recognition," Neural Comput., Vol. 1, no. 4, pp. 541-551, Dec. 1989.
2. Torch7 Android Port. [Online], Available: https://github.com/soumith/torch-android, accessed Sep. 30, 2010.
3. Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, "DeepFace: Closing the gap to human-level performance in face verification," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Washington, DC, USA, Jun. 2014, pp. 1701-1708. [Online], Available: http://dx.doi.org/10.1109/CVPR.2014.220
4. Y Sun, X. Wang, and X. Tang, "Deep learning face representation from predicting 10,000 classes," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2014, pp. 1891-1898.
5. Y Sun, Y Chen, X. Wang, and X. Tang, "Deep learning face representation by joint identification-verification," in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, Eds. Red Hook, NY, USA: Curran Associates, 2014, pp. 1988-1996. [Online], Available: http://papers.nips.cc/paper/5416-deep-learning-face-representation-by-joint-identiflcation-veriflcation.pdf
6. Y Sun, X. Wang, and X. Tang, "Deeply learned face representations are sparse, selective, and robust," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 2892-2900.
7. Y Sun, D. Liang, X. Wang, and X. Tang, "DeepID3: Face recognition with very deep neural networks," CoRR, Feb. 2015. [Online], Available: http://arxiv.org/abs/1502.00873
8. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.
9. C. Szegedy et al., "Going deeper with convolutions," in Proc. IEEE Conf. CVPR, Jun. 2015, pp. 1-9.
10. F. Schroff, D. Kalenichenko, and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 815-823.
11. J. Liu, Y. Deng, T. Bai, Z. Wei, and C. Huang, "Targeting ultimate accuracy: Face recognition via deep embedding," CoRR, Jun. 2015. [Online]. Available: http://arxiv.org/abs/1506.07310
12. D. Yi, Z. Lei, S. Liao, and S. Z. Li, "Learning face representation from scratch," CoRR, Nov. 2014. [Online]. Available: http://arxiv.org/abs/1411.7923
13. J. Ba and R. Caruana, "Do deep nets really need to be deep?" in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, Eds. Red Hook, NY, USA: Curran Associates, 2014, pp. 2654-2662.
14. A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, "FitNets: Hints for thin deep nets," in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.
15. G. Hinton, O. Vinyals, and J. Dean, "Distilling the knowledge in a neural network," CoRR, Mar. 2015. [Online]. Available: http://arxiv.org/abs/1503.02531
16. E. L. Denton, W. Zaremba, J. Bruna, Y. LeCun, and R. Fergus, "Exploiting linear structure within convolutional networks for efficient evaluation," in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, Eds. Red Hook, NY, USA: Curran Associates, 2014, pp. 1269-1277.
17. M. Jaderberg, A. Vedaldi, and A. Zisserman, "Speeding up convolutional neural networks with low rank expansions," in Proc. Brit. Mach. Vis. Conf., 2014.
18. X. Zhang, J. Zou, K. He, and J. Sun, "Accelerating very deep convolutional networks for classification and detection," CoRR, May 2015. [Online]. Available: http://arxiv.org/abs/1505.06798
19. M. Lin, Q. Chen, and S. Yan, "Network in network," in Proc. Int. Conf. Learn. Represent. (ICLR), 2013.
20. Y. LeCun, J. S. Denker, and S. A. Solla, "Optimal brain damage," in Advances in Neural Information Processing Systems 2. San Mateo, CA, USA: Morgan Kaufmann, 1990, pp. 598-605.
21. B. Hassibi and D. G. Stork, "Second order derivatives for network pruning: Optimal brain surgeon," in Advances in Neural Information Processing Systems 5, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Francisco, CA, USA: Morgan Kaufmann, 1992. [Online]. Available: ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/nips-4.bib
22. G. Thimm and E. Fiesler, "Evaluating pruning methods," in Proc. Int. Symp. Artif. Neural Netw., Vol. 2. 1995, pp. 1-4.
23. N. Ström, "Sparse connection and pruning in large dynamic artificial neural networks," in Proc. EUROSPEECH, 1997, pp. 1-4.
24. S. Han, J. Pool, J. Tran, and W. J. Dally, "Learning both weights and connections for efficient neural networks," CoRR, Jul. 2015. [Online]. Available: http://arxiv.org/abs/1506.02626
25. V. Lebedev and V. Lempitsky, "Fast convnets using group-wise brain damage," CoRR, Jun. 2015. [Online]. Available: http://arxiv.org/abs/1506.02515
26. M. Figurnov, D. Vetrov, and P. Kohli. (Apr. 2015). "PerforatedCNNs: Acceleration through elimination of redundant convolutions." [Online]. Available: http://arxiv.org/abs/1504.08362
27. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. (Jul. 2012). "Improving neural networks by preventing co-adaptation of feature detectors." [Online]. Available: http://arxiv.org/abs/1207.0580
28. L. Wan, M. Zeiler, S. Zhang, Y. LeCun, and R. Fergus, "Regularization of neural networks using dropconnect," in Proc. 30th Int. Conf. Mach. Learn. (ICML), 2013, pp. 1058-1066.
29. J. Tompson, R. Goroshin, A. Jain, Y. LeCun, and C. Bregler, "Efficient object localization using convolutional networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 648-656.
30. M. Mathieu, M. Henaff, and Y. LeCun, "Fast training of convolutional networks through FFTs," in Proc. Int. Conf. Learn. Represent. (ICLR), 2014.
31. N. Vasilache, J. Johnson, M. Mathieu, S. Chintala, S. Piantino, and Y. LeCun. (Apr. 2015). "Fast convolutional nets with fbfft: A GPU performance evaluation." [Online]. Available: http://arxiv.org/abs/1412.7580
32. V. Vanhoucke, A. Senior, and M. Z. Mao, "Improving the speed of neural networks on CPUs," in Proc. Deep Learn. Unsupervised Feature Learn. NIPS Workshop, 2011, pp. 1-8.
33. M. Courbariaux, Y. Bengio, and J.-P. David, "Low precision arithmetic for deep learning," CoRR, Vol. abs/1412.7024, 2014. [Online]. Available: http://arxiv.org/abs/1412.7024
34. G. B. Huang and E. Learned-Miller, "Labeled faces in the wild: Updates and new reporting procedures," Dept. Comput. Sci., Univ. Massachusetts Amherst, Amherst, MA, USA, Tech. Rep. UM-CS-2014-003, 2014.
35. D. Chen, X. Cao, L. Wang, F. Wen, and J. Sun, "Bayesian face revisited: A joint formulation," in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 566-579.
36. M. Everingham, J. Sivic, and A. Zisserman, "'Hello! My name is⋯ Buffy' - Automatic naming of characters in TV video," in Proc. Brit. Mach. Vis. Conf., 2006, pp. 1-6.
37. R. Collobert, K. Kavukcuoglu, and C. Farabet, "Torch7: A MATLAB-like environment for machine learning," in Proc. NIPS Workshop BigLearn, 2011.
38. K. He, X. Zhang, S. Ren, and J. Sun. (Feb. 2015). "Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification." [Online]. Available: http://arxiv.org/abs/1502.01852