Advertisement

International Journal of Computer Vision

, Volume 126, Issue 8, pp 855–874 | Cite as

Semi-supervised Region Metric Learning for Person Re-identification

  • Jiawei Li
  • Andy J. Ma
  • Pong C. Yuen
Article
  • 548 Downloads

Abstract

In large-scale camera networks, label information for person re-identification is usually not available under a large amount of cameras due to expensive human labor efforts. Semi-supervised learning could be employed to train a discriminative classifier by using unlabeled data and unmatched image pairs (negatives) generated from non-overlapping camera views, but existing methods suffer from the problem of imbalanced unlabeled data. In this context, this paper proposes a novel semi-supervised region metric learning method to improve person re-identification performance under imbalanced unlabeled data. Firstly, instead of seeking for matched image pairs (positives) from the unlabeled data, we propose to estimate positive neighbors by label propagation with cross person score distribution alignment. Secondly, multiple positive regions are generated using sets of positive neighbors to learn a discriminative region-to-point metric. Experimental results demonstrate that the superiority of the proposed method over existing unsupervised, semi-supervised and person re-identification methods.

Keywords

Person re-identification Semi-supervised learning Imbalanced unlabeled data 

Notes

Acknowledgements

This work is partially supported by Hong Kong RGC General Research Fund HKBU 212313, HKBU 12202514 and SYSU Research Fund 67000-18821116. The authors would like to thank the editor and reviewers for their helpful comments which improve the quality of this paper.

References

  1. Ahmed, E., Jones, M., & Marks, T. K. (2015). An improved deep learning architecture for person re-identification. In The IEEE conference on computer vision and pattern recognition Google Scholar
  2. Bootkrajang, J., & Kabán, A. (2012). Label-noise robust logistic regression and its applications. In Joint European conference on machine learning and knowledge discovery in databases. Springer, Berlin (pp 143–158)Google Scholar
  3. Borgwardt, K. M., Gretton, A., Rasch, M. J., Kriegel, H. P., Scholkopf, B., & Smola, A. J. (2006). Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics, 22, e49–e57.CrossRefGoogle Scholar
  4. Chapelle, O., Schölkopf, B., Zien, A., et al. (2006). Semi-supervised learning. Cambridge: MIT Press.CrossRefGoogle Scholar
  5. Chen, Y., Zhou, X. S., & Huang, T. S. (2001). One-class svm for learning in image retrieval. IEEE International Conference on Image Processing, 1, 34–37.Google Scholar
  6. Chen, Y. C., Zhu, X., Zheng, W. S., & Lai, J. H. (2017). Person re-identification by camera correlation aware feature augmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP(99), 1–1.Google Scholar
  7. Cheng, D., Gong, Y., Zhou, S., Wang, J., & Zheng, N. (2016). Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In IEEE conference on computer vision and pattern recognition.Google Scholar
  8. Chung, D., Tahboub, K., & Delp, E. J. (2017). A two stream siamese convolutional neural network for person re-identification. In The IEEE international conference on computer vision (ICCV) Google Scholar
  9. Farenzena, M., Bazzani, L., Alessandro Perina, V. M., & Cristani, M. (2010). Person re-identification by symmetry-driven accumulation of local features. In IEEE conference on computer vision and pattern recognition, (pp. 2360 –2367)Google Scholar
  10. Figueira, D., Bazzani, L., Minh, H. Q., Cristani, M., Bernardino, A., & Murino, V. (2013). Semi-supervised multi-feature learning for person re-identification. In IEEE international conference on advanced video and signal based surveillance, pp. 111–116.Google Scholar
  11. Frénay, B., & Verleysen, M. (2014). Classification in the presence of label noise: A survey. IEEE Transactions on Neural Networks and Learning Systems, 25(5), 845–869.CrossRefGoogle Scholar
  12. Gheissari, N., Sebastian, T. B., & Hartley, R. (2006). Person reidentification using spatiotemporal appearance. In IEEE conference on computer vision and pattern recognition, pp. 1528–1535.Google Scholar
  13. Gray, D., Brennan, S., & Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. In 10th IEEE international workshop on performance evaluation of tracking and surveillance.Google Scholar
  14. Hirzer, M., Roth, P. M., Köstinger, M., & Bischof, H. (2012). Relaxed pairwise learned metric for person re-identification. In European conference on computer vision, (pp. 780–793)Google Scholar
  15. Jing, X. Y., Zhu, X., Wu, F., You, X., Liu, Q., Yue, D., Hu, R., & Xu, B. (2015). Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning. In IEEE conference on computer vision and pattern recognition, (pp. 695–704).Google Scholar
  16. Kodirov, E., Xiang, T., Fu, Z., & Gong, S. (2016). person re-identification by unsupervised l1 graph learning. In European conference on computer vision.Google Scholar
  17. Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P. M., & Bischof, H. (2012) Large scale metric learning from equivalence constraints. In IEEE conference on computer vision and pattern recognition, (pp. 2288–2295)Google Scholar
  18. Kumar, K., & De Vleeschouwer, C. (2013). Discriminative label propagation for multi-object tracking with sporadic appearance features. In IEEE international conference on computer vision, (pp. 2000–2007).Google Scholar
  19. Kviatkovsky, I., Adam, A., & Rivlin, E. (2013). Color invariants for person reidentification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1622–1634.CrossRefGoogle Scholar
  20. Lan, X., Ma, A. J., & Yuen, P. C. (2014). Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 1194–1201).Google Scholar
  21. Lan, X., Ma, A. J., Yuen, P. C., & Chellappa, R. (2015). Joint sparse representation and robust feature-level fusion for multi-cue visual tracking. IEEE Transactions on Image Processing, 24(12), 5826–5841.MathSciNetCrossRefGoogle Scholar
  22. Lan, X., Zhang, S., Yuen, P. C., & Chellappa, R. (2018). Learning common and feature-specific patterns: A novel multiple-sparse-representation-based tracker. IEEE Transactions on Image Processing, 27(4), 2022–2037.MathSciNetCrossRefGoogle Scholar
  23. Lee, W. S., & Liu, B. (2003). Learning with positive and unlabeled examples using weighted logistic regression. International Conference on Machine Learning, 3, 448–455.Google Scholar
  24. Li, D., Chen, X., Zhang, Z., & Huang, K. (2017). Learning deep context-aware features over body and latent parts for person re-identification. In IEEE conference on computer vision and pattern recognition.Google Scholar
  25. Li, F., Li, G., Yang, N., Xia, F., & Yu, C. (2014). Label matrix normalization for semisupervised learning from imbalanced data. New Review of Hypermedia and Multimedia, 20(1), 5–23.CrossRefGoogle Scholar
  26. Li, S., Wang, Z., Zhou, G., & Lee, S. Y. M. (2011). Semi-supervised learning for imbalanced sentiment classification. In The international joint conference on artificial intelligence, (pp 1826–1831).Google Scholar
  27. Li, W., & Wang, X. (2013). Locally aligned feature transforms across views. In IEEE conference on computer vision and pattern recognition, (pp. 3594–3601).Google Scholar
  28. Li, W., Zhao, R., & Wang, X. (2012). Human reidentification with transferred metric learning. In Proceedings of Asian conference on computer vision.Google Scholar
  29. Li, X., & Liu, B. (2003) Learning to classify texts using positive and unlabeled data. In International joint conference on artificial intelligence, (pp. 587–592).Google Scholar
  30. Liao, S., Hu, Y., Zhu, X., & Li, S. Z. (2015). Person re-identification by local maximal occurrence representation and metric learning. In IEEE conference on computer vision and pattern recognition, (pp. 2197–2206).Google Scholar
  31. Lin, J., Ren, L., Lu, J., Feng, J., & Zhou, J. (2017). Consistent-aware deep learning for person re-identification in a camera network. In IEEE conference on computer vision and pattern recognition.Google Scholar
  32. Lisanti, G., Masi, I., Bagdanov, A. D., & Bimbo, A. D. (2015). Person re-identification by iterative re-weighted sparse ranking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(8), 1629–1642.CrossRefGoogle Scholar
  33. Liu, C., Loy, C., Gong, S., & Wang, G. (2013). Pop: Person re-identification post-rank optimisation. In IEEE international conference on computer vision, (pp. 441–448).Google Scholar
  34. Liu, T., & Tao, D. (2016). Classification with noisy labels by importance reweighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(3), 447–461.MathSciNetCrossRefGoogle Scholar
  35. Liu, X., Song, M., Tao, D., Zhou, X., Chen, C., & Bu, J. (2014). Semi-supervised coupled dictionary learning for person re-identification. In IEEE conference on computer vision and pattern recognition.Google Scholar
  36. Liu, Z., Wang, D., & Lu, H. (2017). Stepwise metric promotion for unsupervised video person re-identification. In The IEEE international conference on computer vision (ICCV).Google Scholar
  37. Ma, A., Li, J., Yuen, P., & Li, P. (2015). Cross-domain person reidentification using domain adaptation ranking svms. IEEE Transactions on Image Processing, 24(5), 1599–1613.MathSciNetCrossRefGoogle Scholar
  38. Ma, A. J., & Li, P. (2014). Semi-supervised ranking for re-identification with few labeled image pairs. In Proceedings of Asian conference on computer vision.Google Scholar
  39. Ma, B., Su, Y., & Jurie, F. (2012). Local descriptors encoded by fisher vectors for person re-identification. In Computer vision ECCV 2012. Workshops and demonstrations.Google Scholar
  40. Mahmood, A., Mian, A., & Owens, R. (2014). Semi-supervised spectral clustering for image set classification. In IEEE conference on computer vision and pattern recognition, (pp 121–128).Google Scholar
  41. Matsukawa, T., Okabe, T., Suzuki, E., & Sato, Y. (2016). Hierarchical gaussian descriptor for person re-identification. In IEEE conference on computer vision and pattern recognition.Google Scholar
  42. Peng, P., Xiang, T., Wang, Y., Pontil, M., Gong, S., Huang, T., & Tian, Y. (2016) Unsupervised cross-dataset transfer learning for person re-identification. In IEEE conference on computer vision and pattern recognition.Google Scholar
  43. Prosser, B., Zheng, W. S., Gong, S., & Xiang, T. (2010). Person re-identification by support vector ranking. In British machine vision conference, (pp. 1–11).Google Scholar
  44. Roth, P., Hirzer, M., Kostinger, M., Beleznai, C., & Bischof, H. (2014). Mahalanobis distance learning for person re-identification. In Person re-identification, advances in computer vision and pattern recognition. London: Springer, pp. 247–267.Google Scholar
  45. Xie, J., & Xiong, T. (2011). Stochastic semi-supervised learning on partially labeled imbalanced data. In Active learning and experimental design workshop in conjunction with AISTATS 2010, (pp. 85–98)Google Scholar
  46. Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., & Li, S. (2014). Salient color names for person re-identification. In European conference on computer vision, (pp. 536–551).Google Scholar
  47. Ye, M., Liang, C., Wang, Z., Leng, Q., & Chen, J. (2015). Ranking optimization for person re-identification via similarity and dissimilarity. In ACM international conference on multimedia, (pp 1239–1242)Google Scholar
  48. Ye, M., Liang, C., Yu, Y., et al. (2016). Person re-identification via ranking aggregation of similarity pulling and dissimilarity pushing. IEEE Transactions on Multimedia, 18, 2553–2566.CrossRefGoogle Scholar
  49. Ye, M., Ma, A. J., Zheng, L., Li, J., & Yuen, P. C. (2017). Dynamic label graph matching for unsupervised video re-identification. In The IEEE international conference on computer vision (ICCV).Google Scholar
  50. Yu, H. X., Wu, A., & Zheng, W. S. (2017). Cross-view asymmetric metric learning for unsupervised person re-identification. In The IEEE international conference on computer vision (ICCV).Google Scholar
  51. Zhao, R., Ouyang, W., & Wang, X. (2013). Unsupervised salience learning for person re-identification. In IEEE conference on computer vision and pattern recognition.Google Scholar
  52. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In IEEE international conference on computer vision, (pp. 1116–1124).Google Scholar
  53. Zheng, W. S., Gong, S., & Xiang, T. (2009). Associating groups of people. In British machine vision conference.Google Scholar
  54. Zheng, W. S., Gong, S., & Xiang, T. (2013). Reidentification by relative distance comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(3), 653–668.CrossRefGoogle Scholar
  55. Zhu, P., Zhang, L., Zuo, W., & Zhang, D. (2013). From point to set: Extend the learning of distance metrics. In IEEE international conference on computer vision, (pp. 2664–2671).Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceHong Kong Baptist UniversityHong KongChina
  2. 2.School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina

Personalised recommendations