Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Uncertainty-optimized deep learning model for small-scale person re-identification

Abstract

In recent years, deep learning has developed rapidly and is widely used in various fields, such as computer vision, speech recognition, and natural language processing. For end-to-end person re-identification, most deep learning methods rely on large-scale datasets. Relatively few methods work with small-scale datasets. Insufficient training samples will affect neural network accuracy significantly. This problem limits the practical application of person re-identification. For small-scale person re-identification, the uncertainty of person representation and the overfitting problem associated with deep learning remain to be solved. Quantifying the uncertainty is difficult owing to complex network structures and the large number of hyperparameters. In this study, we consider the uncertainty of pedestrian representation for small-scale person re-identification. To reduce the impact of uncertain person representations, we transform parameters into distributions and conduct multiple sampling by using multilevel dropout in a testing process. We design an improved Monte Carlo strategy that considers both the average distance and shortest distance for matching and ranking. When compared with state-of-the-art methods, the proposed method significantly improve accuracy on two small-scale person re-identification datasets and is robust on four large-scale datasets.

This is a preview of subscription content, log in to check access.

References

  1. 1

    Zheng L, Shen L Y, Tian L, et al. Scalable person re-identification: a benchmark. In: Proceedings of IEEE International Conference on Computer Vision, 2016. 1116-1124

  2. 2

    Li W, Zhao R, Xiao T, et al. DeepReID: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. 152-159

  3. 3

    Gou M, Karanam S, Liu W, et al. DukeMTMC4ReID: a large-scale multi-camera person re-identification dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1425-1434

  4. 4

    Wei L H, Zhang S L, Gao W, et al. Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 79-88

  5. 5

    Gray D, Tao H. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Proceedings of the European Conference on Computer Vision. Berlin: Springer, 2008. 262–275

  6. 6

    Ma B P, Su Y, Jurie F. Local descriptors encoded by fisher vectors for person re-identification. In: Proceedings of the European Conference on Computer Vision. Berlin: Springer, 2012. 413–422

  7. 7

    Matsukawa T, Okabe T, Suzuki E, et al. Hierarchical gaussian descriptor for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 1363-1372

  8. 8

    Pala F, Satta R, Fumera G, et al. Multimodal person reidentification using RGB-D cameras. IEEE Trans Circuits Syst Video Technol, 2016, 26: 788–799

  9. 9

    Bai S, Tang P, Torr P H S, et al. Re-ranking via metric fusion for object retrieval and person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 740-749

  10. 10

    Yu R, Zhou Z C, Bai S, et al. Divide and fuse: a re-ranking approach for person re-identification. 2017. ArXiv: 1708.04169

  11. 11

    Davis J V, Kulis B, Jain P, et al. Information-theoretic metric learning. In: Proceedings of the 24th International Conference on Machine Learning. New York: ACM, 2007. 209–216

  12. 12

    Köstinger M, Hirzer M, Wohlhart P, et al. Large scale metric learning from equivalence constraints. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2012. 2288-2295

  13. 13

    Xiong F, Gou M, Camps O, et al. Person re-identification using kernel-based metric learning methods. In: Proceedings of the European Conference on Computer Vision, 2014. 1-16

  14. 14

    Varior R R, Haloi M, Wang G. Gated siamese convolutional neural network architecture for human re-identification. In: Proceedings of the European Conference on Computer Vision, 2016. 791-808

  15. 15

    Zheng L, Huang Y J, Lu H C, et al. Pose invariant embedding for deep person re-identification. 2017. ArXiv: 1701.07732

  16. 16

    Cho Y J, Yoon K J. PaMM: pose-aware multi-shot matching for improving person re-identification. 2017. ArXiv: 1705.06011

  17. 17

    Lin Y T, Zheng L, Zheng Z D, et al. Improving person re-identification by attribute and identity learning. 2017. ArXiv: 1703.07220

  18. 18

    Geng M Y, Wang Y W, Xiang T, et al. Deep transfer learning for person re-identification. 2016. ArXiv: 1611.05244

  19. 19

    Jin H B, Wang X B, Liao S C, et al. Deep person re-identification with improved embedding and efficient training. In: Proceedings of IEEE International Joint Conference on Biometrics (IJCB). New York: IEEE, 2017. 261–267

  20. 20

    Zhu J Q, Zeng H Q, Du Y Z, et al. Joint feature and similarity deep learning for vehicle re-identification. IEEE Access, 2018, 6: 43724–43731

  21. 21

    Imani Z, Soltanizadeh H. Histogram of the node strength and histogram of the edge weight: two new features for RGB-D person re-identification. Sci China Inf Sci, 2018, 61: 092108

  22. 22

    Liao S C, Hu Y, Zhu X Y, et al. Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 2197-2206

  23. 23

    Wei L H, Zhang S L, Yao H T, et al. Glad: global-local-alignment descriptor for pedestrian retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia. New York: ACM, 2017. 420–428

  24. 24

    He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 770-778

  25. 25

    Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. In: Proceedings of IEEE International Conference on Computer Vision, 2015. 1-9

  26. 26

    Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. 248-255

  27. 27

    Ahmed E, Jones M, Marks T K. An improved deep learning architecture for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 3908-3916

  28. 28

    Zhang X, Luo H, Fan X, et al. Alignedreid: surpassing human-level performance in person re-identification. 2017. ArXiv: 1711.08184

  29. 29

    Sun Y F, Zheng L, Yang Y, et al. Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision, 2018. 480-496

  30. 30

    Wang G S, Yuan Y F, Chen X, et al. Learning discriminative features with multiple granularities for person reidentification. In: Proceedings of 2018 ACM Multimedia Conference on Multimedia Conference. New York: ACM, 2018. 274–282

  31. 31

    Bai S, Bai X, Tian Q. Scalable person re-identification on supervised smoothed manifold. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 2530-2539

  32. 32

    Yu R, Dou Z Y, Bai S, et al. Hard-aware point-to-set deep metric for person re-identification. In: Proceedings of the European Conference on Computer Vision, 2018. 188-204

  33. 33

    Zheng Z D, Zheng L, Yang Y. A discriminatively learned CNN embedding for person re-identification. ACM Trans Multim Comput Commun Appl, 2017, 14: 13

  34. 34

    Hermans A, Beyer L, Leibe B. In defense of the triplet loss for person re-identification. 2017. ArXiv: 1703.07737

  35. 35

    Zhong Z, Zheng L, Cao D L, et al. Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1318-1327

  36. 36

    Wu L, Hong R C, Wang Y, et al. Cross-entropy adversarial view adaptation for person re-identification. IEEE Trans Circ Syst Video Tech, 2019. doi: https://doi.org/10.1109/TCSVT.2019.2909549

  37. 37

    Liu Z, Wang Y H, Li A N. Hierarchical integration of rich features for video-based person re-identification. IEEE Trans Circuits Syst Video Technol, 2018. doi: https://doi.org/10.1109/TCSVT.2018.2883995

  38. 38

    Zhu Z, Huang T T, Shi B G, et al. Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 2347-2356

  39. 39

    Hou R B, Ma B P, Chang H, et al. VRSTC: occlusion-free video person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 7183-7192

  40. 40

    Chen W H, Chen X T, Zhang J G, et al. A multi-task deep network for person re-identification. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence, 2017

  41. 41

    Zheng Z D, Zheng L, Yang Y. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, 2017. 3754-3762

  42. 42

    Bui T, Hernández-Lobato D, Hernandez-Lobato J, et al. Deep Gaussian processes for regression using approximate expectation propagation. In: Proceedings of International Conference on Machine Learning, 2016. 1472-1481

  43. 43

    Gal Y, Ghahramani Z. Bayesian convolutional neural networks with Bernoulli approximate variational inference. 2015. ArXiv: 1506.02158

  44. 44

    Kwon J, Lee K M. Adaptive visual tracking with minimum uncertainty gap estimation. IEEE Trans Pattern Anal Mach Intell, 2016, 39: 18–31

  45. 45

    Shen F M, Yang Y, Zhou X, et al. Face identification with second-order pooling in single-layer networks. Neurocomputing, 2016, 187: 11–18

  46. 46

    Li Z C, Tang J H. Weakly supervised deep matrix factorization for social image understanding. IEEE Trans Image Process, 2017, 26: 276–288

  47. 47

    Xu Y, Fang X, Li X, et al. Data uncertainty in face recognition. IEEE Trans Cybern, 2014, 44: 1950–1961

  48. 48

    Blundell C, Cornebise J, Kavukcuoglu K, et al. Weight uncertainty in neural networks. 2015. ArXiv: 1505.05424

  49. 49

    Gal Y, Ghahramani Z. Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of International Conference on Machine Learning, 2016. 1050-1059

  50. 50

    Minka T P. A Family of Algorithms for Approximate Bayesian Inference. Cambridge: Massachusetts Institute of Technology, 2001

  51. 51

    Gray D, Brennan S, Tao H. Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), 2007. 3: 1–7

  52. 52

    Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell, 2017, 39: 1137–1149

  53. 53

    Bolle R M, Connell J H, Pankanti S, et al. The relation between the ROC curve and the CMC. In: Proceedings of the 4th IEEE Workshop on Automatic Identification Advanced Technologies (AutoID’05), 2005. 15-20

  54. 54

    Cormack G V, Lynam T R. Statistical precision of information retrieval evaluation. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2006. 533-540

  55. 55

    Ketkar N. Introduction to pytorch. In: Deep Learning With Python. Berkeley: Apress, 2017. 195–208

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (Grant Nos. 61673299, 61203247, 61573259, 61573255, 61876218), Fundamental Research Funds for the Central Universities, and the Open Project Program of the National Laboratory of Pattern Recognition (NLPR). The authors would like to thank the anonymous reviewers for their critical and constructive comments and suggestions.

Author information

Correspondence to Cairong Zhao.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhao, C., Chen, K., Zang, D. et al. Uncertainty-optimized deep learning model for small-scale person re-identification. Sci. China Inf. Sci. 62, 220102 (2019). https://doi.org/10.1007/s11432-019-2675-3

Download citation

Keywords

  • person re-identification
  • uncertainty analysis
  • deep learning