Learning an identity distinguishable space for large scale face recognition

doi:10.19682/j.cnki.1005-8885.2018.0006

中国邮电高校学报(英文版) ›› 2018, Vol. 25 ›› Issue (1): 54-61.doi: 10.19682/j.cnki.1005-8885.2018.0006

• Artificial Intelligence • 上一篇下一篇

Learning an identity distinguishable space for large scale face recognition

岳婷¹,王洪波¹,程时端²

1. 北京邮电大学
2. 北京邮电大学网络与交换技术国家重点实验室

收稿日期:2017-07-17 修回日期:2018-01-15 出版日期:2018-02-28 发布日期:2018-02-28
通讯作者: 王洪波 E-mail:hbwang@bupt.edu.cn
基金资助:
国家863计划;国家自然科学基金;中央高校基本科研业务费专项基金

Learning an identity distinguishable space for large scale face recognition

Received:2017-07-17 Revised:2018-01-15 Online:2018-02-28 Published:2018-02-28
Contact: Hong-Bo WANG E-mail:hbwang@bupt.edu.cn
Supported by:
;Natural Science Foundation of China

摘要/Abstract

摘要： Implementing face recognition efficiently to real world large scale dataset presents great challenges to existing approaches.The method in this paper was proposed to learn an identity distinguishable space for large scale face recognition in MSR- Bing image recognition challenge (IRC). Firstly, a deep convolutional neural network (CNN) was used to optimize a 128 B embedding for large scale face retrieval. The embedding was trained via using triplets of aligned face patches from FaceScrub and CASIA-WebFace datasets. Secondly, the evaluation of MSR-Bing IRC was conducted according to a cross-domain retrieval scheme. The real-time retrieval in this paper was benefited from the K-means clustering performed on the feature space of training data. Furthermore, a large scale similarity learning (LSSL) was applied on the relevant face images for learning a better identity space. A novel method for selecting similar pairs was proposed for LSSL. Compared with many existing networks of face recognition, the proposed model was lightweight and the retrieval method was promising as well.

关键词:

Abstract: Implementing face recognition efficiently to real world large scale dataset presents great challenges to existing approaches.The method in this paper was proposed to learn an identity distinguishable space for large scale face recognition in MSR- Bing image recognition challenge (IRC). Firstly, a deep convolutional neural network (CNN) was used to optimize a 128 B embedding for large scale face retrieval. The embedding was trained via using triplets of aligned face patches from FaceScrub and CASIA-WebFace datasets. Secondly, the evaluation of MSR-Bing IRC was conducted according to a cross-domain retrieval scheme. The real-time retrieval in this paper was benefited from the K-means clustering performed on the feature space of training data. Furthermore, a large scale similarity learning (LSSL) was applied on the relevant face images for learning a better identity space. A novel method for selecting similar pairs was proposed for LSSL. Compared with many existing networks of face recognition, the proposed model was lightweight and the retrieval method was promising as well.

Key words: face recognition, convolutional neural network (CNN), triplet loss, inception, similarity learning

参考文献

1. Lu C C, Tang X O. Surpassing human-level face verification performance on LFW with GaussianFace. Proceedings of the 29th AAAI Conference on Artificial Intelligence, Jan 25-30, 2015, Austin, TX, USA. Menlo Park, CA, USA: American Association for Artificial Intelligence (AAAI), 2015: 3811-3819

2. Parkhi O M, Vedaldi A, Zisserman A. Deep face recognition. Proceedings of the British Machine Vision Conference, Sept 7-10, 2015, Swansea, UK. 2015: 41.1-41.12

3. Lin S L, Zhao Z C, Su F. Homemade TS-net for automatic face recognition. Proceedings of the 2016 ACM International Conference on Multimedia Retrieval (ICMR’16), Jun 6-9, 2016, New York, NY, USA. New York, NY, USA: ACM, 2016: 135-142

4. Taigman Y, Yang M, Ranzato M A, et al. DeepFace: Closing the gap to human-level performance in face verification. Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14), Jun 23-28, 2014, Columbus, OH, USA. Piscataway, NJ, USA: IEEE, 2014: 1701-1708

5. Sun Y, Wang X G, Tang X O. Deep learning face representation from predicting 10,000 classes. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14), Jun 23-28, 2014, Columbus, OH, USA. Piscataway, NJ, USA: IEEE, 2014: 1891-1898

6. Yi D, Lei Z, Liao S C, et al. Learning face representation from scratch. Computer Science, 2014, arXiv:1411.7923v1/1-10

7. Guo Y D, Zhang L, Hu Y X, et al. MS-Celeb-1M: Challenge of recognizing one million celebrities in the real world. Proceedings of the 2016 IS&T International Symposium on Electronic Imaging, Feb 14-18, 2016, San Francisco, CA, USA. 2016: 6p

8. Schroff F, Kalenichenko D, Philbin J. FaceNet: A unified embedding for face recognition and clustering. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), Jun 7-12, 2015, Boston, MA, USA. Piscataway, NJ, USA: IEEE, 2015: 815-823

9. Bhattarai B, Sharma G, Jurie F. CP-mtML: Coupled projection multi-task metric learning for large scale face retrieval. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), Jun 26-Jul 1, 2016, Las Vegas, NV, USA. Piscataway, NJ, USA: IEEE, 2016: 4226-4235

10. Weinberger K Q, Saul L K. Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research, 2009, 10: 207-244

11. Zeiler M D, Fergus R. Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision (ECCV’14), Sept 6-12, 2014, Zurich, Switzerland. 2014: 818-833

12. Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), Jun 7-12, 2015, Boston, MA, USA. Piscataway, NJ, USA: IEEE, 2015: 1-9

13. Qiao J Y. On the preimages of parabolic periodic points. Nonlinearity, 2000, 13(3): 813-818

14. Martins Carlos L F, Garcia Rosa J L. Face recognition through a chaotic neural network model. Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN'14), Jul 6-11, 2014, Beijing, China. Piscataway, NJ, USA: IEEE, 2014: 859-863

15. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML’15), Jul 6-11, 2015, Lille, France. 2015: 448-456

16. Amos B, Ludwiczuk B, Satyanarayanan M. OpenFace: A general-purpose face recognition library with mobile applications. CMU-CS-16-118. Pittsburgh, PA, USA: School of Computer Science, Carnegie Mellon University, 2016

17. Yang Y, Liao S C, Lei Z, et al. Large scale similarity learning using similar pairs for person verification. Proceedings of the 30th AAAI Conference on Artificial Intelligence, Feb 12-17, 2016, Phoenix, AZ, USA. Menlo Park, CA, USA: American Association for Artificial Intelligence (AAAI), 2016: 3655-3661

18. Köstinger M, Hirzer M, Wohlhart P, et al. Large scale metric learning from equivalence constraints. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12), Jun 16-21, 2012, Providence, RI, USA. Piscataway, NJ, USA: IEEE, 2012: 2288-2295

Learning an identity distinguishable space for large scale face recognition

Learning an identity distinguishable space for large scale face recognition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价