Advertisement

Faster Person Re-identification

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12353)

Abstract

Fast person re-identification (ReID) aims to search person images quickly and accurately. The main idea of recent fast ReID methods is the hashing algorithm, which learns compact binary codes and performs fast Hamming distance and counting sort. However, a very long code is needed for high accuracy (e.g. 2048), which compromises search speed. In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy. It uses shorter codes to coarsely rank broad matching similarities and longer codes to refine only a few top candidates for more accurate instance ReID. Specifically, we design an All-in-One (AiO) framework together with a Distance Threshold Optimization (DTO) algorithm. In AiO, we simultaneously learn and enhance multiple codes of different lengths in a single model. It learns multiple codes in a pyramid structure, and encourage shorter codes to mimic longer codes by self-distillation. DTO solves a complex threshold search problem by a simple optimization process, and the balance between accuracy and speed is easily controlled by a single parameter. It formulates the optimization target as a \(F_{\beta }\) score that can be optimised by Gaussian cumulative distribution functions. Experimental results on 2 datasets show that our proposed method (CtF) is not only \(8\%\) more accurate but also \(5\times \) faster than contemporary hashing ReID methods. Compared with non-hashing ReID methods, CtF is \(50\times \) faster with comparable accuracy. Code is available at https://github.com/wangguanan/light-reid.

Notes

Acknowledgement

This work was supported in part by the National Key R&D Program of China (Grant 2018YFC2001700), by the National Natural Science Foundation of China (Grants 61720106012, and U1913601), by the Beijing Natural Science Foundation (Grants L172050), by the Strategic Priority Research Program of Chinese Academy of Sciences (Grant XDB32040000), by the Youth Innovation Promotion Association of CAS (2020140), the Alan Turing Institute Turing Fellowship, and Vision Semantics Ltd.

References

  1. 1.
    Bajpai, K., Kots, A.: Implementing and analyzing an efficient version of counting sort (e-counting sort). Int. J. Comput. Appl.98(9) (2014)Google Scholar
  2. 2.
    Cao, Y., Long, M., Liu, B., Wang, J.: Deep cauchy hashing for hamming space retrieval. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1229–1237 (2018)Google Scholar
  3. 3.
    Cao, Z., Long, M., Wang, J., Yu, P.S.: HashNet: deep learning to hash by continuation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5609–5618 (2017)Google Scholar
  4. 4.
    Chen, J., Wang, Y., Qin, J., Liu, L., Shao, L.: Fast person re-identification via cross-camera semantic binary transformation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5330–5339 (2017)Google Scholar
  5. 5.
    Chen, J., Wang, Y., Wu, R.: Person re-identification by distance metric learning to discrete hashing. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 789–793 (2016)Google Scholar
  6. 6.
    Datar, M., Immorlica, N., Indyk, P., Mirrokni, V.S.: Locality-sensitive hashing scheme based on p-stable distributions. In: Scg 2004: Proceedings of the Twentieth Symposium on Computational Geometry, pp. 253–262 (2004)Google Scholar
  7. 7.
    Fang, W., Hu, H.M., Hu, Z., Liao, S., Li, B.: Perceptual hash-based feature description for person re-identification. Neurocomputing 272(1), 520–531 (2018)CrossRefGoogle Scholar
  8. 8.
    Gong, S., Cristani, M., Yan, S., Loy, C.C.: Person re-identification (2014)Google Scholar
  9. 9.
    Goutte, C., Gaussier, E.: A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In: Losada, D.E., Fernández-Luna, J.M. (eds.) ECIR 2005. LNCS, vol. 3408, pp. 345–359. Springer, Heidelberg (2005).  https://doi.org/10.1007/978-3-540-31865-1_25CrossRefGoogle Scholar
  10. 10.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  11. 11.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
  12. 12.
    Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
  13. 13.
    Hoare, C.A.: Quicksort. Comput. J. 5(1), 10–16 (1962)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1062–1071 (2018)Google Scholar
  15. 15.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  16. 16.
    Koestinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2288–2295. IEEE (2012)Google Scholar
  17. 17.
    Kulis, B., Darrell, T.: Learning to hash with binary reconstructive embeddings. In: International Conference on Neural Information Processing Systems, pp. 1042–1050 (2009)Google Scholar
  18. 18.
    Lai, H., Pan, Y., Liu, Y., Yan, S.: Simultaneous feature learning and hash coding with deep neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
  19. 19.
    Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 817–824 (2011)Google Scholar
  20. 20.
    Li, W.J., Wang, S., Kang, W.C.: Feature learning based deep supervised hashing with pairwise labels. In: International Joint Conference on Artificial Intelligence, pp. 1711–1717 (2016)Google Scholar
  21. 21.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: 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 (2015)Google Scholar
  22. 22.
    Liao, S., Li, S.Z.: Efficient PSD constrained asymmetric metric learning for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3685–3693 (2015)Google Scholar
  23. 23.
    Liu, W., Wang, J., Ji, R., Jiang, Y.G.: Supervised hashing with kernels. In: Computer Vision and Pattern Recognition, pp. 2074–2081 (2012)Google Scholar
  24. 24.
    Liu, Z., Qin, J., Li, A., Wang, Y., Gool, L.V.: Adversarial binary coding for efficient person re-identification. In: 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 700–705 (2019)Google Scholar
  25. 25.
    Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)Google Scholar
  26. 26.
    Ma, B., Su, Y., Jurie, F.: Covariance descriptor based on bio-inspired features for person re-identification and face verification. Image Vis. Comput. 32(6–7), 379–390 (2014)CrossRefGoogle Scholar
  27. 27.
    Qian, X., et al.: Pose-normalized image generation for person re-identification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 661–678 (2018)Google Scholar
  28. 28.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Sarfraz, M.S., Schumann, A., Eberle, A., Stiefelhagen, R.: A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 420–429 (2018)Google Scholar
  30. 30.
    Shen, F., Shen, C., Liu, W., Shen, H.T.: Supervised discrete hashing. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 37–45 (2015)Google Scholar
  31. 31.
    Sun, Y., et al.: Perceive where to focus: learning visibility-aware part-level features for partial person re-identification, pp. 393–402 (2019)Google Scholar
  32. 32.
    Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 480–496 (2018)Google Scholar
  33. 33.
    Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1365–1374 (2019)Google Scholar
  34. 34.
    Wang, G., Hu, Q., Cheng, J., Hou, Z.: Semi-supervised generative adversarial hashing for image retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 469–485 (2018)Google Scholar
  35. 35.
    Wang, G., et al.: High-order information matters: learning relation and topology for occluded person re-identification. arXiv preprint arXiv:2003.08177 (2020)
  36. 36.
    Wang, G., Yang, Y., Cheng, J., Wang, J., Hou, Z.: Color-sensitive person re-identification. In: IJCAI 2019 Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 933–939 (2019)Google Scholar
  37. 37.
    Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z.: RGB-infrared cross-modality person re-identification via joint pixel and feature alignment. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3622–3631 (2019)Google Scholar
  38. 38.
    Wang, G., Zhang, T., Yang, Y., Cheng, J., Chang, J., Hou, Z.: Cross-modality paired-images generation for RGB-infrared person re-identification. In: AAAI 2020 : The Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)Google Scholar
  39. 39.
    Wang, J., Kumar, S., Chang, S.F.: Semi-supervised hashing for large-scale search. IEEE Trans. Pattern Anal. Mach. Intell. 34(12), 2393–2406 (2012)CrossRefGoogle Scholar
  40. 40.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: International Conference on Neural Information Processing Systems, pp. 1753–1760 (2008)Google Scholar
  41. 41.
    Wu, L., Wang, Y., Ge, Z., Hu, Q., Li, X.: Structured deep hashing with convolutional neural networks for fast person re-identification. Comput. Vis. Image Underst. 167, 63–73 (2017)CrossRefGoogle Scholar
  42. 42.
    Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning (2014)Google Scholar
  43. 43.
    Yang, Y., Yang, J., Yan, J., Liao, S., Yi, D., Li, S.Z.: Salient color names for person re-identification. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 536–551. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_35CrossRefGoogle Scholar
  44. 44.
    Zhang, R., Lin, L., Zhang, R., Zuo, W., Zhang, L.: Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 24(12), 4766 (2015)MathSciNetCrossRefGoogle Scholar
  45. 45.
    Zhao, F., Huang, Y., Wang, L., Tan, T.: Deep semantic ranking based hashing for multi-label image retrieval. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1556–1564 (2015)Google Scholar
  46. 46.
    Zhao, Y., Luo, S., Yang, Y., Song, M.: DeepSSH: deep semantic structured hashing for explainable person re-identification. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1653–1657 (2018)Google Scholar
  47. 47.
    Zheng, F., Shao, L.: Learning cross-view binary identities for fast person re-identification. In: IJCAI 2016 Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 2399–2406 (2016)Google Scholar
  48. 48.
    Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose-invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28(9), 4500–4509 (2019)MathSciNetCrossRefGoogle Scholar
  49. 49.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)Google Scholar
  50. 50.
    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)
  51. 51.
    Zheng, W.S., Gong, S., Xiang, T.: Reidentification by relative distance comparison. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 653–668 (2013)CrossRefGoogle Scholar
  52. 52.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. arXiv preprint arXiv:1701.07717 (2017), https://academic.microsoft.com/paper/2949257576
  53. 53.
    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. arXiv preprint arXiv:1708.04896 (2017)
  54. 54.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5157–5166 (2018). https://academic.microsoft.com/paper/2963289251
  55. 55.
    Zhu, F., Kong, X., Zheng, L., Fu, H., Tian, Q.: Part-based deep hashing for large-scale person re-identification. IEEE Trans. Image Process. 26(10), 4806–4817 (2017)MathSciNetCrossRefGoogle Scholar
  56. 56.
    Zhu, X., Wu, B., Huang, D., Zheng, W.S.: Fast open-world person re-identification. IEEE Trans. Image Process. 27(5), 2286–2300 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The State Key Laboratory of Management and Control of Complex System, Institute of AutomationChinese Academy of Sciences (CAS)BeijingChina
  2. 2.Queen Mary University of LondonLondonUK
  3. 3.School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijingChina
  4. 4.National Laboratory of Pattern Recognition, Institute of Automation, CASBeijingChina
  5. 5.CAS Center for Excellence in Brain Science and Intelligence TechnologyBeijingChina

Personalised recommendations