Skip to main content

Advertisement

Springer Nature Link
Log in

Deep feature learning with mixed distance maximization for person Re-identification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In despite of several advanced approaches, deep learning for person re-identification is still regarded as a challenging task due to local optima in the objective function of the deep networks in addition to various changes of poses and viewpoints etc. We introduced a novel neural network learning, or deep feature learning with mixed distance maximization, to solve the local optima problem in person re-identification. A local objective function is first defined to maximize the intra-distance among a triplet for person re-identification. Also, a global objective function is proposed to consider distances among triplets. Based on two objective functions, a main objective function is introduced to make full use of the information of triplets. This main objective function is defined based on the combination of two distances, called a mixed distance. This mixed distance can prevent that the triplets become close to each other and the matched pairs in each triplets become apart in deep learning with the relative distance comparison. We test our deep method with the mixed distance maximization on several datasets. Experimental results demonstrate that deep feature learning with the mixed distance maximization have promising discriminative capability in comparison with other ones.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Chen D et al (2018) Group consistent similarity learning via deep CRF for person Re-identification. In: CVPR, pp 8649–8658

  2. Chen Y et al (2014) Deep learning face representation by joint identification-verification. In: NIPS, pp 1988–1996

  3. Chen Y et al (2018) Person Re-Identification by Camera Correlation Aware Feature Augmentation. IEEE Trans Pattern Anal Mach Intell 40(2):392–408

    Article  MathSciNet  Google Scholar 

  4. Cheng D et al (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: CVPR, pp 1335–1344

  5. Choe G et al (2016) Combined salience based person Re-identification. Multimedia Tools and Applications 75(18)

  6. Ding S, Lin L, Wang G, Chao H (2015) Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn 18:2993–3003

    Article  Google Scholar 

  7. Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPR, IEEE, pp 2360–2367

  8. Hirzer M, Roth P, Kostinger M, Bischof H (2012) Relaxed pairwise learned metric for person re-identification. ECCV

  9. Kostinger M, Hirzer M, Wohlhart P, Rorth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: CVPR. IEEE, pp 2288–2295

  10. Li W, Zhao R, Xiao T, Wang X (2014) Deep ReID: Deep filter pairing neural network for person re-identification. In: CVPR, pp 152–159

  11. Li Z, Chang S, Liang F, Huang T, Cao L, Smith J (2013) Learning locally-adaptive decision functions for person verification. In: CVPR, IEEE, pp 3610–3617

  12. Lin L, Liu X, Zhu S (2010) Layered graph matching with composite cluster sampling. IEEE Trans Pattern Anal Mach Intell 32(8):1426–1442

    Article  Google Scholar 

  13. Lin L, Wu T, Porway J, Xu Z (2009) A stochastic graph grammar for compositional object representation and recognition. Pattern Recogn 42(7):1297–1307

    Article  MATH  Google Scholar 

  14. Liu C et al (2012) Person re-identification: what features are important. In: ECCV, Springer, pp 391–401

  15. Liu H, Ma B, Qin L, Pang J, Zhang C, Huang Q (2015) Set-label modeling anddeep metric learning on person re-identification. Neurocomputing 151:1283–1292

    Article  Google Scholar 

  16. Liu J et al (2016) Multi-scale triplet cnn for person re-identification. In: ACM on Multimedia Conference, pp 192–196

  17. Ma B et al (2012) Bicov: a novel image representation for person re-identification and face verification. In: BMVC

  18. Ma B, Su Y, Jurie F (2012) Local descriptors encoded by fisher vectors for person re-identification

  19. Ma L, Yang X, Tao D (2014) Person re-identification over camera networks using multi-task distance metric learning. IEEE Trans Image Process 23(8):3656–3670

    Article  MathSciNet  MATH  Google Scholar 

  20. Madheswari K, Venkateswaran N (2016) An optimal weighted averaging fusion strategy for thermal and visible images using dual tree discrete wavelet transform and self tunning particle swarm optimization. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-016-4030-x

  21. Mignon A, Jurie F (2012) A new approach for distance learning from sparse pairwise constraints. In: CVPR, IEEE, pp 2666–2672

  22. Pedagadi S, Orwell J, Velastin S, Boghossian B (2013) Local fisher discriminant analysis for pedestrian re-identification. In: CVPR. IEEE, pp 3318–3325

  23. Schroff F, Kalenichenko D, Philbin J (2015) A unified embedding for face recognition and clustering. In: CVPR, pp 815–823

  24. Schwartz W, Davis L (2009) Learning discriminative appearance-based models using partial least squares. In: XXII Brazilian symposium on computer graphics and image processing (SIBGRAPI)

  25. Wei L et al (2018) Person transfer GAN to bridge domain gap for person Re-identification. In: CVPR, pp 79–88

  26. Wu Y et al (2017) Sampling matters in deep embedding learning. In: CVPR, pp 2840–2848

  27. Yi D et al (2014) Deep metric learning for person re-identification. In: ICPR, pp 34–39

  28. Yi D, Lei Z, Li S Deep metric learning for practical person re-identification. arXiv:1407.4979

  29. Zhao R et al (2013) Learning mid-level filters for person re-identification. In: CVPR, pp 144–151

  30. Zhao R et al (2013) Person re-identification by salience matching. In: ICCV. IEEE, pp 2528–2535

  31. Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: CVPR, IEEE, pp 4321–4328

  32. Zheng W, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPR, IEEE, pp 649–656

  33. Zheng W, Gong S, Xiang T (2013) Re-identification by relative distance comparison. IEEE Trans Pattern Anal Mach Intell 35(3):653–668

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Visual Information Processing Laboratory, School of Computer Science and Technology, Kim Il Sung University, Pyongyang, Democratic People’s Republic of Korea

    Chunhwa Choe, Gwangmin Choe & Sokmin Han

  2. Intelligent and Distributed Computing Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China

    Tianjiang Wang & Caihong Yuan

Authors
  1. Chunhwa Choe
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Gwangmin Choe
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Tianjiang Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Sokmin Han
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Caihong Yuan
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Gwangmin Choe.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Choe, C., Choe, G., Wang, T. et al. Deep feature learning with mixed distance maximization for person Re-identification. Multimed Tools Appl 78, 27719–27741 (2019). https://doi.org/10.1007/s11042-019-07867-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-07867-9

Keywords