Hessian Regularized Distance Metric Learning for People Re-Identification

Abstract

Distance metric learning is a vital issue in people re-identification. Although numerous algorithms have been proposed, it is still challenging especially when the labeled information is few. Manifold regularization can take advantage of labeled and unlabeled information and achieve promising performance in a unified metric learning framework. In this paper, we propose Hessian regularized distance metric learning for people re-identification. Particularly, the second-order Hessian energy prefers functions whose values vary linearly with respect to geodesic distance. Hence Hessian regularization allows us to preserve the geometry of the intrinsic data probability distribution better and then promotes the performance when there is few labeled information. We conduct extensive experiments on the popular VIPeR dataset, CUHK Campus dataset and CUHK03 dataset. The encouraging results suggest that manifold regularization can boost distance metric learning and the proposed Hessian regularized distance metric learning algorithm outperforms the traditional manifold regularized distance metric learning algorithms including graph Laplacian regularization algorithm.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Xiong F, Gou M, Camps O et al (2014) Person re-identification using Kernel-based metric learning methods. European Conference on Computer Vision. Springer, Cham, pp 1–16

    Google Scholar 

  2. 2.

    Zhao R, Oyang W, Wang X (2016) Person re-identification by saliency learning. IEEE Trans Pattern Anal Mach Intell 39(2):356–370

    Article  Google Scholar 

  3. 3.

    Chen F, Chai J, Ren D et al (2017) Semi-supervised distance metric learning for person re-identification. In: International conference on computer and information science. IEEE, pp 733–738

  4. 4.

    Zheng W S, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: Computer vision and pattern recognition. IEEE, pp 649–656

  5. 5.

    Koestinger M, Hirzer M, Wohlhart P et al (2012) Large scale metric learning from equivalence constraints. In: Computer vision and pattern recognition. IEEE, pp 2288–2295

  6. 6.

    Tao D, Jin L, Wang Y et al (2013) Person re-identification by regularized smoothing kiss metric learning. IEEE Trans Circuits Syst Video Technol 23(10):1675–1685

    Article  Google Scholar 

  7. 7.

    Zhao C, Chen Y, Wei Z et al (2018) QRKISS: A two-stage metric learning via QR-decomposition and KISS for person re-identification. In: Neural Processing Letters, pp 1–24

    Article  Google Scholar 

  8. 8.

    Mignon A, Jurie F (2012) Pcca: a new approach for distance learning from sparse pairwise constraints. In: Computer vision and pattern recognition. IEEE, pp 2666–2672

  9. 9.

    Lu X, Wang Y, Zhou X et al (2016) A method for metric learning with multiple-kernel embedding. Neural Process Lett 43(3):905–921

    Article  Google Scholar 

  10. 10.

    Hu L, Hu J, Ye Z et al (2018) Performance analysis for SVM combining with metric learning. In: Neural processing letters, pp 1–22

    Article  Google Scholar 

  11. 11.

    Kodirov E, Xiang T, Gong S (2015) Dictionary learning with iterative Laplacian regularisation for unsupervised person re-identification. In: British machine vision conference, pp 44.1–44.12

  12. 12.

    Peng P, Xiang T, Wang Y et al (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1306–1315

  13. 13.

    Yu H X, Wu A, Zheng W S (2017) Cross-view asymmetric metric learning for unsupervised person re-identification. In: IEEE international conference on computer vision. IEEE, pp 994–1002

  14. 14.

    Liu W, Ma S, Tao D et al (2010) Semi-supervised sparse metric learning using alternating linearization optimization. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1139–1148

  15. 15.

    Niu G, Dai B, Yamada M et al (2012) Information-theoretic semi-supervised metric learning via entropy regularization. Neural Comput 26(8):1717–1762

    MathSciNet  Article  Google Scholar 

  16. 16.

    Hoi SCH, Liu W, Chang SF (2008) Semi-supervised distance metric learning for collaborative image retrieval. In: Computer Vision and Pattern Recognition. IEEE, pp 1–7

  17. 17.

    Jin R, Wang S, Zhou Y (2009) Regularized distance metric learning: theory and algorithm. In: Advances in neural information processing systems, pp 862–870

  18. 18.

    Shi H, Luo Y, Xu C et al (2015) Manifold Regularized Transfer Distance Metric Learning. In: British machine vision conference, pp 158.1–158.11

  19. 19.

    Kim K I, Steinke F, Hein M (2009) Semi-supervised regression using Hessian energy with an application to semi-supervised dimensionality reduction. In: Adv Neural Inf Process Syst pp 979–987

  20. 20.

    Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of IEEE international workshop on performance evaluation for tracking and surveillance (PETS), pp 1–7

  21. 21.

    Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. Asian Conference on Computer Vision. Springer, Berlin, pp 31–44

    Google Scholar 

  22. 22.

    Li W, Zhao R, Xiao T et al (2014) DeepReID: Deep filter pairing neural network for person re-identification. In: Computer vision and pattern recognition. IEEE, pp 152–159

  23. 23.

    Liao S, Hu Y, Zhu X et al (2015) Person re-identification by Local Maximal Occurrence representation and metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2197–2206

  24. 24.

    Zhao R, Ouyang W, Wang X (2013) Person re-identification by salience matching. Proc IEEE Int Conf Comput Vision 2013:2528–2535

    Google Scholar 

  25. 25.

    Zeng M, Wu Z, Tian C et al (2015) Efficient person re-identification by hybrid spatiogram and covariance descriptor. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 48–56

  26. 26.

    Zhao R, Ouyang W, Wang X (2014) Learning Mid-level Filters for Person Re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 144–151

  27. 27.

    Geng Y, Hu HM, Zeng G et al (2015) A person re-identification algorithm by exploiting region-based feature salience. J Vis Commun Image Represent 29:89–102

    Article  Google Scholar 

  28. 28.

    Ma B, Su Y (2012) Local descriptors encoded by fisher vectors for person re-identification. European Conference on Computer Vision. Springer, Berlin, pp 413–422

    Google Scholar 

  29. 29.

    Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 3586–3593

  30. 30.

    Leng Q, Hu R, Liang C et al (2015) Person re-identification with content and context re-ranking. Multimedia Tools Appl 74(17):6989–7014

    Article  Google Scholar 

  31. 31.

    Hirzer M, Roth PM, Bischof H (2012) Person re-identification by efficient impostor-based metric learning. In: Advanced video and signal-based surveillance (AVSS). IEEE, pp 203–208

  32. 32.

    Farenzena M, Bazzani L, Perina A et al (2010) Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition. IEEE, pp 2360–2367

  33. 33.

    Weinberger KQ, Saul LK (2008) Fast solvers and efficient implementations for distance metric learning. In: Proceedings of the 25th international conference on machine learning. ACM, pp 1160–1167

  34. 34.

    Davis J V, Kulis B, Jain P et al (2007) Information-theoretic metric learning. In: Proceedings of the 24th international conference on machine learning. ACM, pp 209–216

  35. 35.

    Xing E P, Jordan M I, Russell S J et al (2003) Distance metric learning with application to clustering with side-information. In: Advances in neural information processing systems, pp 521–528

  36. 36.

    Guillaumin M, Verbeek J, Schmid C (2009) Is that you? Metric learning approaches for face identification. In: ICCV 2009-international conference on computer vision. IEEE, pp 498–505

  37. 37.

    McFee B, Lanckriet G R (2010) Metric learning to rank. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 775–782

Download references

Acknowledgements

This work is supported the National Natural Science Foundation of China under Grant 61671480, in part by the Fundamental Research Funds for the Central Universities, China University of Petroleum (East China) under Grant 18CX07011A.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Weifeng Liu.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Feng, G., Liu, W., Tao, D. et al. Hessian Regularized Distance Metric Learning for People Re-Identification. Neural Process Lett 50, 2087–2100 (2019). https://doi.org/10.1007/s11063-019-10000-4

Download citation

Keywords

  • Metric learning
  • Person re-identification
  • Hessian energy
  • Manifold regularization