Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3533–3550 | Cite as

Person re-identification by the asymmetric triplet and identification loss function

Article
  • 276 Downloads

Abstract

Person re-identification(re-id) aims to match the same individuals across different non-overlapping camera views. In this paper, we analyze the effectiveness of two widely used triplet loss and softmax loss on person re-id task. We conclude that the triplet loss function is suitable for the relatively small datasets with the shallow neural network, while the softmax loss works better on larger datasts with relatively deeper network architecture. Both of them are essential to the person re-id task. Moreover, we present a convolutional neural network (CNN) model under the joint supervision of the triplet loss and softmax loss for person re-id. This method can get a slightly better performance than either of them. The triplet loss makes the distance of the same individual’s images closer, and pushes the instances of different individuals far apart from each other, which can effectively reduce the intra-personal variations. Meanwhile, the person identification cost, which is implemented by the softmax loss with the “center loss” embedded, can discriminatively learn some identity-related feature representations (i.e. features with large inter-personal variations). Extensive experimental results demonstrate the effectiveness of our proposed method, and we have obtained promising performance on the challenging i-LIDS, PRID2011 and CUHK03 datasets.

Keywords

Person re-identification Triplet loss Joint Identification 

Notes

Acknowledgements

This work was supported by the National Basic Research Program of China (Grant No.2015CB351705), the State Key Program of National Natural Science Foundation of China (Grant No.61332018).

References

  1. 1.
    Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. CVPR 5:25Google Scholar
  2. 2.
    Bak S, Corvee E, Brémond F, Thonnat M (2010) Person re-identification using spatial covariance regions of human body parts. In: Seventh IEEE international conference on advanced video and signal based surveillance (AVSS), 2010, pp 435–440Google Scholar
  3. 3.
    Chang X, Yang Y (2016) Semi-supervised feature analysis by mining correlations among multiple tasks. IEEE Trans Neural Netw Learn Syst.  https://doi.org/10.1109/TNNLS.2016.2582746
  4. 4.
    Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-k projections for bilinear analysis. IEEE Trans Neural Netw Learn Syst 27(7):1502–1513MathSciNetCrossRefGoogle Scholar
  5. 5.
    Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process 26(5):3911–3920MathSciNetCrossRefGoogle Scholar
  6. 6.
    Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann AG (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Transactions on Cybernetics 47(5):1180–1197CrossRefGoogle Scholar
  7. 7.
    Chang X, Yu Y-L, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(8):1617–1632CrossRefGoogle Scholar
  8. 8.
    Cheng DS, Cristani M, Stoppa M, Bazzani L, Murino V (2011) Custom pictorial structures for re-identification. In: BMVC, vol 1, p 6Google Scholar
  9. 9.
    Cheng D, Chang X, Liu L, Hauptmann AG, Gong Y, Zheng N (2017) Discriminative dictionary learning with ranking metric embedded for person re-identification. In: IJCAI, pp 964–970Google Scholar
  10. 10.
    Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: ICML, pp 209–216Google Scholar
  11. 11.
    Ding S, Lin L, Wang G et al (2015) Deep feature learning with relative distance comparison for person re identification. Pattern Recogn 48(10):2993–3003CrossRefGoogle Scholar
  12. 12.
    Dollár P, Tu Z, Tao H, Belongie S (2007) Feature mining for image classification. In: CVPR, pp 1–8Google Scholar
  13. 13.
    Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp 2360–2367Google Scholar
  14. 14.
    Gheissari N, Sebastian TB, Hartley R (2006) Person reidentification using spatiotemporal appearance. In: CVPR, vol 2, pp 1528–1535Google Scholar
  15. 15.
    Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp 580–587Google Scholar
  16. 16.
    Globerson A, Roweis ST (2005) Metric learning by collapsing classes. In: NIPS, pp 451–458Google Scholar
  17. 17.
    Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: ECCV, pp 262–275Google Scholar
  18. 18.
    Guillaumin M, Verbeek J, Schmid C (2009) Is that you? Metric learning approaches for face identification. In: CVPR, pp 498–505Google Scholar
  19. 19.
    Hirzer M, Beleznai C, Roth PM, Bischof H (2011) Person re-identification by descriptive and discriminative classification. In: Image analysis, pp 91–102Google Scholar
  20. 20.
    Hirzer M, Roth PM, Bischof H (2012) Person re-identification by efficient impostor-based metric learning. In: IEEE ninth international conference on advanced video and signal-based surveillance (AVSS), 2012, pp 203–208Google Scholar
  21. 21.
    Hu W, Hu M, Zhou X, Tan T, Lou J, Maybank S (2006) Principal axis-based correspondence between multiple cameras for people tracking. IEEE Trans Pattern Anal Mach Intell 28(4):663– 671CrossRefGoogle Scholar
  22. 22.
    Khamis S, Kuo C-H, Singh VK, Shet VD, Davis LS (2014) Joint learning for attribute-consistent person re-identification. In: ECCV, pp 134–146Google Scholar
  23. 23.
    Koestinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: CVPR, pp 2288–2295Google Scholar
  24. 24.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: NIPS, pp 1097–1105Google Scholar
  25. 25.
    Li W, Wang X (2013) Locally aligned feature transforms across views. In: CVPR, pp 3594–3601Google Scholar
  26. 26.
    Li Z, Chang S, Liang F, Huang TS, Cao L, Smith JR (2013) Learning locally-adaptive decision functions for person verification. In: CVPR, pp 3610–3617Google Scholar
  27. 27.
    Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: CVPR, pp 152–159Google Scholar
  28. 28.
    Ma B, Su Y, Jurie F (2012) Bicov: a novel image representation for person re-identification and face verification. In: BMVC, p 11Google Scholar
  29. 29.
    McLaughlin N, Martinez del Rincon J, Miller P (2016) Recurrent convolutional network for video-based person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1325–1334Google Scholar
  30. 30.
    Paisitkriangkrai S, Shen C, van den Hengel A Learning to rank in person re-identification with metric ensembles. arXiv:1503.01543
  31. 31.
    Park U, Jain AK, Kitahara I, Kogure K, Hagita N (2006) Vise: visual search engine using multiple networked cameras. In: ICPR, vol 3, pp 1204–1207Google Scholar
  32. 32.
    Roth PM, Hirzer M, Köstinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In: Person re-identification, pp 247–267Google Scholar
  33. 33.
    Schroff F, Kalenichenko D, Philbin J Facenet: a unified embedding for face recognition and clustering. arXiv:1503.03832
  34. 34.
    Schwartz WR, Davis LS (2009) Learning discriminative appearance-based models using partial least squares. In: XXII Brazilian symposium on computer graphics and image processing (SIBGRAPI), 2009, pp 322–329Google Scholar
  35. 35.
    Sun Y, Chen Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. In: NIPS, pp 1988–1996Google Scholar
  36. 36.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9Google Scholar
  37. 37.
    UK (2008) Home office i-lids multiple camera tracking scenario definitionGoogle Scholar
  38. 38.
    Varior RR, Haloi M, Wang G (2016) Gated siamese convolutional neural network architecture for human re-identification. In: European conference on computer vision. Springer, pp 791–808Google Scholar
  39. 39.
    Wang X, Doretto G, Sebastian T, Rittscher J, Tu P (2007) Shape and appearance context modeling. In: ICCV, pp 1–8Google Scholar
  40. 40.
    Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, Chen B, Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: CVPR, pp 1386–1393Google Scholar
  41. 41.
    Weinberger KQ, Blitzer J, Saul LK (2005) Distance metric learning for large margin nearest neighbor classification. In: NIPS, pp 1473–1480Google Scholar
  42. 42.
    Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: European conference on computer vision. Springer, pp 499–515Google Scholar
  43. 43.
    Xiao Q, Cao K, Chen H, Peng F, Zhang C Cross domain knowledge transfer for person re-identification. arXiv:1611.06026
  44. 44.
    Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1249–1258Google Scholar
  45. 45.
    Xing EP, Jordan MI, Russell S, Ng AY (2002) Distance metric learning with application to clustering with side-information. In: NIPS, pp 505–512Google Scholar
  46. 46.
    Xiong F, Gou M, Camps O, Sznaier M (2014) Person re-identification using kernel-based metric learning methods. In: ECCV, pp 1–16Google Scholar
  47. 47.
    Yan Y, Ni B, Song Z, Ma C, Yan Y, Yang X (2016) Person re-identification via recurrent feature aggregation. In: European conference on computer vision. Springer, pp 701–716Google Scholar
  48. 48.
    Yang Y, Yang J, Yan J, Liao S, Yi D, Li SZ (2014) Salient color names for person re-identification. In: ECCV, pp 536–551Google Scholar
  49. 49.
    Yi D, Lei Z, Liao S, Li SZ (2014) Deep metric learning for person re-identification. In: ICPR, pp 34–39Google Scholar
  50. 50.
    Zhang D, Han J, Han J, Shao L (2016) Cosaliency detection based on intrasaliency prior transfer and deep intersaliency mining. IEEE Transactions on Neural Networks and Learning Systems 27(6):1163–1176MathSciNetCrossRefGoogle Scholar
  51. 51.
    Zhang D, Han J, Li C, Wang J, Li X (2016) Detection of co-salient objects by looking deep and wide. Int J Comput Vis 120(2):215–232MathSciNetCrossRefGoogle Scholar
  52. 52.
    Zhao R, Ouyang W, Wang X (2013) Person re-identification by salience matching. In: ICCV, pp 2528–2535Google Scholar
  53. 53.
    Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: CVPR, pp 3586–3593Google Scholar
  54. 54.
    Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In: CVPR, pp 144–151Google Scholar
  55. 55.
    Zheng W-S, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPR, pp 649–656Google Scholar
  56. 56.
    Zheng Z, Zheng L, Yang Y A discriminatively learned cnn embedding for person re-identification. arXiv:1611.05666
  57. 57.
    Zhu L, Shen J, Jin H, Xie L, Zheng R (2015) Landmark classification with hierarchical multi-modal exemplar feature. IEEE Trans Multimedia 17(7):981–993CrossRefGoogle Scholar
  58. 58.
    Zhu L, Shen J, Liu X et al (2016) Learning compact visual representation with canonical views for robust mobile landmark search. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence. AAAI Press, pp 3959–3965Google Scholar
  59. 59.
    Zhu L, Shen J, Xie L et al (2016) Unsupervised topic hypergraph hashing for efficient mobile image retrieval. IEEE Trans CybernGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • De Cheng
    • 1
  • Yihong Gong
    • 1
  • Weiwei Shi
    • 1
  • Shizhou Zhang
    • 1
  1. 1.The Institute of Artificial Intelligence and Robotic, School of Electronic and Information EngineeringXi’an Jiaotong UniversityShaanxiChina

Personalised recommendations