Browse > Article
http://dx.doi.org/10.9717/kmms.2020.23.8.1019

Compressed Ensemble of Deep Convolutional Neural Networks with Global and Local Facial Features for Improved Face Recognition  

Yoon, Kyung Shin (Department of Computer and Electronic Systems Engineering, Hankuk University of Foreign Studies)
Choi, Jae Young (Department of Computer and Electronic Systems Engineering, Hankuk University of Foreign Studies)
Publication Information
Journal of Korea Multimedia Society / v.23, no.8, 2020 , pp. 1019-1029 More about this Journal
Abstract
In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.
Keywords
Face Recognition; Local Features; Global Features; Soft Target; Ensemble Neural Network; Knowledge Distillation; Deep Convolution Neural Network;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L.F. Fei, "ImageNet: A Large-scale Hierarchical Image Database," Computer Vision and Pattern Recognition, pp. 248-255, 2009.
2 K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition," arXiv Preprint arXiv:1409.1556, 2014.
3 L. Rokach, “Ensemble-based Classifiers,” Artificial Intelligence Review, Vol. 33, No. 1-2, pp. 1-39, 2010.   DOI
4 A. Canziani, A. Paszke, and E. Culurciello, "An Analysis of Deep Neural Network Models for Practical Applications," arXiv Preprint arXiv:1605.07678, 2016.
5 C. Bucilua, R. Caruana, and A. Niculescu-Mizil, "Model Compression," Proceedings of the 12th ACM Special Interest Group on Knowledge Discovery in Data International Conference on Knowledge Discovery and Data Mining, pp. 535-541, 2006.
6 H.A. Khan, "Feature Fusion and Classifier Ensemble Technique for Robust Face Recognition," Signal Processing: An International Journal, Vol. 11, pp. 1-15, 2017.
7 G. Hinton, O. Vinyals, and J. Dean, "Distilling the Knowledge in a Neural Network," arXiv Preprint arXiv:1503.02531, 2015.
8 Y. Su, S. Shan, X. Chen, and W. Gao, “Hierarchical Ensemble of Global and Local Classifiers for Face Recognition,” IEEE Transactions Image Processing, Vol. 18, No. 8, pp. 1885-1886, 2009.   DOI
9 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
10 W.C. Cheng, T.Y. Wu, and D.W. Li, "Ensemble Convolutional Neural Networks for Face Recognition," Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence, pp. 1-6, 2018.
11 T. Fukuda, M. Suzuki, G. Kurata, S. Thomas, J. Cui, and B. Ramabhadran, "Efficient Knowledge Distillation from an Ensemble of Teachers," Interspeech, pp. 3697-3701, 2017.
12 Y. Feng, H. Wang, D.T. Yi, and R. Hu, "Triplet Distillation for Deep Face Recognition," arXiv Preprint arXiv:1905.04457, 2019.
13 J. Yim, D. Joo, J. Bae, and J. Kim, "A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4133-4141, 2017.
14 K.T. Kim, and J.Y. Choi, “Using Spatial Pyramid Based Local Descriptor for Face Recognition,” Journal of Korea Multimedia Society, Vol. 20, No. 5, pp. 758-768, 2017.   DOI
15 U. Asif, J. Tang, and S. Harrer, "Ensemble Knowledge Distillation for Learning Improved and Efficient Networks," arXiv Preprint arXiv: 1909.08097, 2019.
16 J. Karlekar, J. Feng, Z.S. Wong, and S. Pranata, "Deep Face Recognition Model Compression via Knowledge Transfer and Distillation," arXiv Preprint arXiv:1906.00619, 2019.
17 P.J. Phillips, H. Moon, S.A. Rizvi, and P.J. Rauss, “The FERET Evaluation Methodology for Face Recognition Algorithms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 10, pp. 1090-1104, 2000.   DOI