ABSTRACT
On specific face dataset, such as the LFW benchmark, recent face recognition methods have achieved near perfect accuracy. However, the face identification is still a challenging task for a super large scale dataset, where a real application is urgently needed, thus Microsoft challenge of recognizing one million celebrities (MS-Celeb-1M) has attracted an increasing attention. In this paper, we propose a three-step strategy to address this problem. Firstly, based on a corss-domain face dataset, i.e., the CASIA-Web dataset, an efficient and deliberate face representation model with a Max-Feature-Map (MFM) activation function is trained to map raw images into the feature space quickly. Secondly, face representations with the same MID in MS-Celeb-1M are clustered into three subsets: a pure set, a hard set and a mess set. The cluster centers are used as gallery representations of the corresponding MID and this scheme reduces the impact of noisy images and the number of comparisons during the face matching. Finally, locality sensitive hashing (LSH) algorithm is applied to speed up the search of the nearest centroid. Experimental results show that our face CNN model can extract stable and discriminative face representations, and the proposed three-step strategy achieves a promising performance without any manual selection for the MS-Celeb-1M dataset. Furthermore, we find that via clustering a relatively pure set is kept by many MIDs in MS-Celeb-1M, which indicats this scheme is effective for cleaning a huge but mess dataset.
- D. Chen, X. Cao, L. Wang, F. Wen, and J. Sun. Bayesian face revisited: A joint formulation. In Computer Vision-ECCV 2012, pages 566--579. Springer, 2012. Google ScholarDigital Library
- D. Chen, X. Cao, F. Wen, and J. Sun. Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification. In Computer-Vision and Pattern, Recognition (CVPR), 2013 IEEE Conference on, pages 3025--3032. IEEE, 2013. Google ScholarDigital Library
- Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao. Ms-celeb-1m: Challenge of recognizing one million celebri-ties in the real world.Google Scholar
- G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical report, Technical Report 07-49, University of Massachusetts, Amherst, 2007.Google Scholar
- I. Kemelmacher-Shlizerman, S. Seitz, D. Miller, and E. Brossard. The megaface benchmark: 1 million faces for recognition at scale. arXiv preprint arXiv:1512.00596, 2015.Google Scholar
- C. Lu and X. Tang. Surpassing human-level face verification performance on lfw with gaussianface. arXiv preprint arXiv:1404.3840, 2014. Google ScholarDigital Library
- J. MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, pages 281--297. Oakland, CA, USA., 1967.Google Scholar
- O. M. Parkhi, A. Vedaldi, and A. Zisserman. Deep face recognition. In British Machine Vision Conference, volume 1, page 6, 2015.Google ScholarCross Ref
- P. J. Phillips, H. Moon, S. Rizvi, P. J. Rauss, et al. The feret evaluation methodology for face-recognition algorithms. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(10):1090--1104, 2000. Google ScholarDigital Library
- F. Schroff, D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 815--823, 2015.Google ScholarCross Ref
- T. Sim, S. Baker, and M. Bsat. The cmu pose, illumination, and expression (pie) database. In Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on, pages 46--51. IEEE, 2002. Google ScholarDigital Library
- M. Slaney and M. Casey. Locality-sensitive hashing for finding nearest neighbors {lecture notes}. IEEE Signal Processing Magazine, 25(2):128--131, 2008.Google ScholarCross Ref
- Y. Sun, Y. Chen, X. Wang, and X. Tang. Deep learning face representation by joint identification-verification. In Advances in Neural Information Processing Systems, pages 1988--1996, 2014. Google ScholarDigital Library
- Y. Sun, X. Wang, and X. Tang. Hybrid deep learning for face verification. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages 1489--1496. IEEE, 2013. Google ScholarDigital Library
- Y. Sun, X. Wang, and X. Tang. Deep learning face representation from predicting 10,000 classes. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages 1891--1898. IEEE, 2014. Google ScholarDigital Library
- Y. Sun, X. Wang, and X. Tang. Deeply learned face representations are sparse, selective, and robust. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2892--2900, 2015.Google ScholarCross Ref
- Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages 1701--1708. IEEE, 2014. Google ScholarDigital Library
- L. Wolf, T. Hassner, and I. Maoz. Face recognition in unconstrained videos with matched background similarity. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 529--534. IEEE, 2011. Google ScholarDigital Library
- X. Wu, R. He, and Z. Sun. A lightened cnn for deep face representation. arXiv preprint arXiv:1511.02683, 2015.Google Scholar
- D. Yi, Z. Lei, S. Liao, and S. Z. Li. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014.Google Scholar
Recommendations
Deep representation alignment network for pose-invariant face recognition
AbstractWith the recent developments in convolutional neural networks and the increasing amount of data, there has been great progress in face recognition. Nevertheless, unconstrained situations remain challenging, given their variations in ...
Deep compact discriminative representation for unconstrained face recognition
AbstractConvolutional Neural Network has been widely used in pattern recognition community, especially face recognition. Loss function, as a supervisory signal to learn a CNN model, plays an important role in obtaining the desired facial ...
Highlights- Two losses are for compact and discriminative deep face features.
- The intra-...
Face Recognition Based on Deep Learning
Human Centered ComputingAbstractAs one of the non-contact biometrics, face representation had been widely used in many circumstances. However conventional methods could no longer satisfy the demand at present, due to its low recognition accuracy and restrictions of many ...
Comments