Skip to main content
SpringerLink
Log in

Rapid Person Re-Identification via Sub-space Consistency Regularization

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Person Re-Identification (ReID) matches pedestrian across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation as well as complex quick-sort algorithms. Recently, some works propose to yield binary encoded person descriptors which instead only require fast Hamming distance computation and simple counting-sort algorithms. However, the performances of such binary encoded descriptors, especially with short code (e.g, 32 and 64 bits), are hardly satisfactory given the sparse binary space. To strike a balance between the model accuracy and efficiency, we propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25 times than real-value features under same dimensions whilst maintain a competitive accuracy, especially under short codes. SCR transforms real-value features vector (e.g, 2048 float32) with short binary codes (e.g, 64 bits) by first dividing real-value features vector into M sub-spaces, each with C clustered centroids. Thus the distance between two samples can be expressed as the summation of respective distance to the centroids, which can be sped up by offline calculation and maintained via a look-up-table. On the other side, these real-value centroids help to achieve significantly higher accuracy than using binary code. Lastly, we convert the distance look-up-table to be integer and apply the counting-sort algorithm to speed up the ranking stage. We also propose a novel consistency regularization with an iterative framework. Experimental results on Market-1501 and DukeMTMC-reID show promising and exciting results. Under short code, our proposed SCR enjoys Real-value-level accuracy and Hashing-level speed.

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

Access this article

Log in via an institution

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
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Bajpai K, Kots A (2014) Implementing and analyzing an efficient version of counting sort (e-counting sort). Int J Comput Appl 98:1–2

    Google Scholar 

  2. Cao Z, Long M, Wang J, et al (2017) Hashnet: deep learning to hash by continuation. In: ICCV, pp 5609–5618

  3. Chen J, Wang Y, Wu R (2016) Person re-identification by distance metric learning to discrete hashing. In: ICIP, pp 789–793

  4. Chen J, Wang Y, Qin J, et al (2017) Fast person re-identification via cross-camera semantic binary transformation. In: CVPR, pp 5330–5339

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

  6. Ding G, Zhang S, Khan S, et al (2018) Center based pseudo-labeling for semi-supervised person re-identification. In: ICME

  7. Ding G, Khan S, Tang Z et al (2019) Feature mask network for person re-identification. Pattern Recogn Lett 137:91

    Article  Google Scholar 

  8. Ding G, Zhang S, Khan S et al (2019) Feature affinity based pseudo labeling for semi-supervised person re-identification. IEEE Trans Multim 21(11):2891–2902

    Article  Google Scholar 

  9. Fang W, Hu HM, Hu Z et al (2017) Perceptual hash-based feature description for person re-identification. Neurocomputing 272:520

    Article  Google Scholar 

  10. Farenzena M, Bazzani L, Perina A, et al (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp 2360–2367

  11. Feng G, Liu W, Tao D et al (2019) Hessian regularized distance metric learning for people re-identification. Neural Process Lett 50(3):2087–2100

    Article  Google Scholar 

  12. Gong S, Cristani M, Yan S, et al (2013) Person Re-Identification

  13. He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778

  14. Hoare CA (1962) Quicksort. Comput J 5(1):10–16

    Article  MathSciNet  MATH  Google Scholar 

  15. Kalayeh MM, Basaran E, Gokmen M, et al (2018) Human semantic parsing for person re-identification. In: CVPR, pp 1062–1071

  16. Köstinger M, Hirzer M, Wohlhart P, et al (2012) Large scale metric learning from equivalence constraints. In: CVPR, pp 2288–2295

  17. Li D, Hu R, Huang W et al (2021) Trajectory association for person re-identification. Neural Process Lett 53(5):3267–3285

    Article  Google Scholar 

  18. Li H, Pang J, Tao D et al (2021) Cross adversarial consistency self-prediction learning for unsupervised domain adaptation person re-identification. Inf Sci 559:46–60

    Article  Google Scholar 

  19. Li H, Dong N, Yu Z et al (2022) Triple adversarial learning and multi-view imaginative reasoning for unsupervised domain adaptation person re-identification. IEEE Transa Circuits Syst Video Technol 32(5):2814–2830

    Article  MathSciNet  Google Scholar 

  20. Li Y, Lin C, Lin Y, et al (2019) Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: ICCV, pp 7918–7928

  21. Liao S, Li SZ (2015) Efficient psd constrained asymmetric metric learning for person re-identification. In: ICCV, pp 3685–3693

  22. Liao S, Shao L (2022) Graph sampling based deep metric learning for generalizable person re-identification. In: CVPR

  23. Liao S, Hu Y, Zhu X, et al (2015) Person re-identification by local maximal occurrence representation and metric learning. In: CVPR, pp 2197–2206

  24. Lin Y, Dong X, Zheng L, et al (2019) A bottom-up clustering approach to unsupervised person re-identification. In: AAAI, pp 1–8

  25. Liu Z, Qin J, Li A, et al (2019) Adversarial binary coding for efficient person re-identification. In: ICME, pp 700–705

  26. Luo H, Gu Y, Liao X, et al (2019) Bag of tricks and a strong baseline for deep person re-identification. In: CVPR Workshops

  27. Nister D, Stewenius H (2006) Scalable recognition with a vocabulary tree. In: CVPR, pp 2161–2168

  28. Qian X, Fu Y, Xiang T, et al (2018) Pose-normalized image generation for person re-identification. In: ECCV, pp 650–667

  29. Ratcliffe JG (1994) Foundations of hyperbolic manifolds

  30. Sarfraz MS, Schumann A, Eberle A, et al (2018) A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In: CVPR, pp 420–429

  31. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: ICLR

  32. Sun Y, Zheng L, Yang Y, et al (2018) Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV, pp 501–518

  33. Sun Y, Xu Q, Li Y, et al (2019) Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification. In: CVPR, pp 393–402

  34. Tan H, Liu X, Tian S, et al (2020) Mhsa-net: Multi-head self-attention network for occluded person re-identification. arXiv:2008.04015

  35. Wang G, Zhang T, Cheng J, et al (2019) Rgb-infrared cross-modality person re-identification via joint pixel and feature alignment. In: ICCV

  36. Wang G, Gong S, Cheng J, et al (2020) Faster person re-identification. In: ECCV

  37. Wang G, Yang S, Liu H, et al (2020a) High-order information matters: Learning relation and topology for occluded person re-identification. In: CVPR

  38. Wang G, Yang Y, Zhang T et al (2020) Cross-modality paired-images generation and augmentation for rgb-infrared person re-identification. Neural Netw 128:294–304

    Article  Google Scholar 

  39. Wang G, Zhang T, Yang Y, et al (2020) Cross-modality paired-images generation for rgb-infrared person re-identification. In: AAAI

  40. Wang G, Hu Q, Yang Y, et al (2021) Adversarial binary mutual learning for semi-supervised deep hashing. IEEE Transactions on Neural Networks and Learning Systems pp 1–15

  41. Wang H, Bi X (2021) Person re-identification based on graph relation learning. Neural Process Lett 53(2):1401–1415

    Article  Google Scholar 

  42. Wu C, Ge W, Wu A, et al (2022) Camera-conditioned stable feature generation for isolated camera supervised person re-identification. In: CVPR

  43. Wu L, Wang Y, Ge Z, et al (2018) Structured deep hashing with convolutional neural networks for fast person re-identification. arXiv:1702.04179

  44. Xiang X, Lv N, Zhai M et al (2020) Dual-path part-level method for visible-infrared person re-identification. Neural Process Lett 52(1):313–328

    Article  Google Scholar 

  45. Yao Y, Chen T, Xie GS, et al (2021a) Non-salient region object mining for weakly supervised semantic segmentation. In: CVPR, pp 2623–2632

  46. Yin HF, Wu XJ, Song X (2021) Competitive non-negative representation with image gradient orientations for face recognition. Neural Process Lett 54:657

    Article  Google Scholar 

  47. Yin Q, Wang G, Ding G, et al (2021b) Multi-view label prediction for unsupervised learning person re-identification. IEEE Signal Processing Letters pp 1–1

  48. Yin Q, Wang G, Wu J et al (2022) Dynamic re-weighting and cross-camera learning for unsupervised person re-identification. Mathematics 10(10):1654

    Article  Google Scholar 

  49. Lin L, Zhang R, Zhang R et al (2015) Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Trans Image Process 24(12):4766–4779

    Article  MathSciNet  MATH  Google Scholar 

  50. Zhang X, Yang Y, Li T et al (2021) CMC: A consensus multi-view clustering model for predicting Alzheimer’s Disease Progression. Computer Methods and Programs in Biomedicine 199:105895

    Article  Google Scholar 

  51. Zhao C, Chen Y, Wei Z et al (2019) Qrkiss: a two-stage metric learning via qr-decomposition and kiss for person re-identification. Neural Process Lett 49(3):899–922

    Article  Google Scholar 

  52. Zhao Y, Li Y, Wang S (2019) Open-world person re-identification with deep hash feature embedding. IEEE Signal Process Lett 26(12):1758–1762

    Article  Google Scholar 

  53. Zheng F, Shao L (2016) Learning cross-view binary identities for fast person re-identification. In: IJCAI, pp 2399-2406

  54. Zheng L, Shen L, Tian L, et al (2015) Scalable person re-identification: a benchmark. In: ICCV, pp 1116–1124

  55. Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. arXiv:1610.02984

  56. Zheng WS, Gong S, Xiang T (2013) Reidentification by relative distance comparison. IEEE Trans Pattern Ana Mach Intell 35(3):653–668

    Article  Google Scholar 

  57. Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: ICCV

  58. Zhong Z, Zheng L, Zheng Z, et al (2018) Camera style adaptation for person re-identification. In: CVPR, pp 5157–5166

  59. Zhou W, Lian C, Zeng Z et al (2021) Improve semi-supervised learning with metric learning clusters and auxiliary fake samples. Neural Process Lett 53(5):3427–3443

    Article  Google Scholar 

  60. Zhu F, Kong X, Zheng L, et al (2017) Part-based deep hashing for large-scale person re-identification. IEEE Transactions on Image Processing pp 1–1

Download references

Author information

Authors and Affiliations

  1. The Collaborative Innovation Center of Social Safety Science and Technology, Nanjing University of Science and Technology, Xiaolingwei Street, Nanjing, 210094, Jiangsu, China

    Qingze Yin & Zhenmin Tang

  2. Institute of Automation, Chinese Academy of Sciences, Beijing, 100045, China

    Guan’an Wang

  3. School of Computing, National University of Singapore, Singapore, Singapore

    Guodong Ding

  4. Department, The Queen Mary University of London, London, E1 4NS, UK

    Qilei Li & Shaogang Gong

Authors
  1. Qingze Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guan’an Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Guodong Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qilei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shaogang Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhenmin Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qingze Yin.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yin, Q., Wang, G., Ding, G. et al. Rapid Person Re-Identification via Sub-space Consistency Regularization. Neural Process Lett 55, 3149–3168 (2023). https://doi.org/10.1007/s11063-022-11002-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-022-11002-5

Keywords

Search

Navigation