Person Re-identification with Neural Architecture Search

  • Shizhou Zhang
  • Rui Cao
  • Xing Wei
  • Peng WangEmail author
  • Yanning Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11857)


Most of the existing person re-identification (ReID) methods use a classification network pre-trained on external data as the backbone and then fine-tune it, which results in a network architecture that is fixed and dependent on pre-training of external data. There are also some methods that are specifically designed by human experts for ReID, but manual network design becomes more difficult as network requirements increase and often fails to achieve optimal settings. In this paper, we consider using emerging neural architecture search (NAS) technology as a tool to solve above problems. However, most of NAS methods deal with classification tasks, which causes NAS to not be directly extended to ReID. In order to coordinate the inconsistency between the two optimization goals, we propose to establish an objective function with the assistant of the triplet loss to guide the direction of architecture search. Finally, it is no longer dependent on external data to automatically generate a ReID network with excellent performance using NAS directly on the target dataset. The experimental results on three public datasets validate that our method can automatically and efficiently find the network architecture suitable for ReID.


Person re-identification Neural architecture search 


  1. 1.
    Ahmed, E., Jones, M., Marks, T.K.: An improved deep learning architecture for person re-identification. In: CVPR (2015)Google Scholar
  2. 2.
    Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NETVLAD: CNN architecture for weakly supervised place recognition. In: CVPR, pp. 5297–5307 (2016)Google Scholar
  3. 3.
    Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: ICLR (2017)Google Scholar
  4. 4.
    Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: CVPR (2016)Google Scholar
  5. 5.
    Elsken, T., Metzen, J.H., Hutter, F.: Simple and efficient architecture search for convolutional neural networks. In: ICLR (2018)Google Scholar
  6. 6.
    Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. 20, 55:1–55:21 (2019)MathSciNetzbMATHGoogle Scholar
  7. 7.
    Geng, M., Wang, Y., Xiang, T., Tian, Y.: Deep transfer learning for person re-identification. CoRR (2016)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  9. 9.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. CoRR (2017)Google Scholar
  10. 10.
    Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR (2016)Google Scholar
  11. 11.
    Kandasamy, K., Neiswanger, W., Schneider, J., Póczos, B., Xing, E.P.: Neural architecture search with Bayesian optimisation and optimal transport. In: NeurIPS, pp. 2020–2029 (2018)Google Scholar
  12. 12.
    Kim, E., Hannan, D., Kenyon, G.: Deep sparse coding for invariant multimodal halle berry neurons. In: CVPR (2018)Google Scholar
  13. 13.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  14. 14.
    Lavi, B., Serj, M.F., Ullah, I.: Survey on deep learning techniques for person re-identification task. CoRR (2018)Google Scholar
  15. 15.
    Li, D., Chen, X., Zhang, Z., Huang, K.: Learning deep context-aware features over body and latent parts for person re-identification. In: CVPR, pp. 7398–7407 (2017)Google Scholar
  16. 16.
    Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: CVPR (2014)Google Scholar
  17. 17.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: CVPR, pp. 2197–2206 (2015)Google Scholar
  18. 18.
    Lin, J., Ren, L., Lu, J., Feng, J., Zhou, J.: Consistent-aware deep learning for person re-identification in a camera network. In: CVPR, pp. 3396–3405 (2017)Google Scholar
  19. 19.
    Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Yang, Y.: Improving person re-identification by attribute and identity learning. CoRR (2017)Google Scholar
  20. 20.
    Liu, C., et al.: Progressive neural architecture search. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 19–35. Springer, Cham (2018). Scholar
  21. 21.
    Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. CoRR (2018)Google Scholar
  22. 22.
    Luo, R., Tian, F., Qin, T., Liu, T.: Neural architecture optimization. CoRR (2018)Google Scholar
  23. 23.
    Negrinho, R., Gordon, G.J.: DeepArchitect: automatically designing and training deep architectures. CoRR (2017)Google Scholar
  24. 24.
    Paisitkriangkrai, S., Shen, C., van den Hengel, A.: Learning to rank in person re-identification with metric ensembles. In: CVPR (2015)Google Scholar
  25. 25.
    Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. In: The International Conference on Machine Learning (ICML), pp. 4092–4101 (2018)Google Scholar
  26. 26.
    Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. CoRR (2018)Google Scholar
  27. 27.
    Real, E., et al.: Large-scale evolution of image classifiers. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6–11 August 2017, pp. 2902–2911 (2017)Google Scholar
  28. 28.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). Scholar
  29. 29.
    Shen, Y., Xiao, T., Li, H., Yi, S., Wang, X.: End-to-end deep Kronecker-product matching for person re-identification. In: CVPR (2018)Google Scholar
  30. 30.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)Google Scholar
  31. 31.
    Su, C., Li, J., Zhang, S., Xing, J., Gao, W., Tian, Q.: Pose-driven deep convolutional model for person re-identification. In: ICCV (2017)Google Scholar
  32. 32.
    Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)Google Scholar
  33. 33.
    Varior, R.R., Haloi, M., Wang, G.: Gated siamese convolutional neural network architecture for human re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 791–808. Springer, Cham (2016). Scholar
  34. 34.
    Wei, X., Zhang, Y., Gong, Y., Zhang, J., Zheng, N.: Grassmann pooling as compact homogeneous bilinear pooling for fine-grained visual classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 365–380. Springer, Cham (2018). Scholar
  35. 35.
    Wei, X., Zhang, Y., Gong, Y., Zheng, N.: Kernelized subspace pooling for deep local descriptors. In: CVPR, pp. 1867–1875 (2018)Google Scholar
  36. 36.
    Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR, pp. 3376–3385 (2017)Google Scholar
  37. 37.
    Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. CoRR (2018)Google Scholar
  38. 38.
    Yi, D., Lei, Z., Liao, S., Li, S.Z.: Deep metric learning for person re-identification. In: ICPR, pp. 34–39 (2014)Google Scholar
  39. 39.
    Zhang, H., Kiranyaz, S., Gabbouj, M.: Finding better topologies for deep convolutional neural networks by evolution. CoRR (2018)Google Scholar
  40. 40.
    Zhang, S., Zhang, Q., Wei, X., Zhang, Y., Xia, Y.: Person re-identification with triplet focal loss. IEEE Access 6, 78092–78099 (2018)CrossRefGoogle Scholar
  41. 41.
    Zhao, H., eet al.: Spindle net: Person re-identification with human body region guided feature decomposition and fusion. In: CVPR, pp. 907–915 (2017)Google Scholar
  42. 42.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124 (2015)Google Scholar
  43. 43.
    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. CoRR (2016)Google Scholar
  44. 44.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV, pp. 3774–3782 (2017)Google Scholar
  45. 45.
    Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR, pp. 3652–3661 (2017)Google Scholar
  46. 46.
    Zhou, J., Yu, P., Tang, W., Wu, Y.: Efficient online local metric adaptation via negative samples for person re-identification. In: ICCV, pp. 2439–2447 (2017)Google Scholar
  47. 47.
    Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: ICLR (2017)Google Scholar
  48. 48.
    Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR, pp. 8697–8710 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Shizhou Zhang
    • 1
  • Rui Cao
    • 2
  • Xing Wei
    • 3
  • Peng Wang
    • 1
    Email author
  • Yanning Zhang
    • 1
  1. 1.National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer ScienceNorthwestern Polytechnical UniversityXi’anChina
  2. 2.School of Information Science and TechnologyNorthwest UniversityXi’anChina
  3. 3.Institute of Artificial Intelligence and Robotics, College of Artificial IntelligenceXi’an Jiaotong UniversityXi’anChina

Personalised recommendations