Advertisement

Rethinking the Distribution Gap of Person Re-identification with Camera-Based Batch Normalization

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12357)

Abstract

The fundamental difficulty in person re-identification (ReID) lies in learning the correspondence among individual cameras. It strongly demands costly inter-camera annotations, yet the trained models are not guaranteed to transfer well to previously unseen cameras. These problems significantly limit the application of ReID. This paper rethinks the working mechanism of conventional ReID approaches and puts forward a new solution. With an effective operator named Camera-based Batch Normalization (CBN), we force the image data of all cameras to fall onto the same subspace, so that the distribution gap between any camera pair is largely shrunk. This alignment brings two benefits. First, the trained model enjoys better abilities to generalize across scenarios with unseen cameras as well as transfer across multiple training sets. Second, we can rely on intra-camera annotations, which have been undervalued before due to the lack of cross-camera information, to achieve competitive ReID performance. Experiments on a wide range of ReID tasks demonstrate the effectiveness of our approach. The code is available at https://github.com/automan000/Camera-based-Person-ReID.

Keywords

Person re-identification Distribution gap Camera-based batch normalization 

Notes

Acknowledgements

This work was supported by National Science Foundation of China under grant No. 61521002.

Supplementary material

504453_1_En_9_MOESM1_ESM.pdf (245 kb)
Supplementary material 1 (pdf 244 KB)

References

  1. 1.
    Almazan, J., Gajic, B., Murray, N., Larlus, D.: Re-id done right: towards good practices for person re-identification. arXiv preprint arXiv:1801.05339 (2018)
  2. 2.
    Chang, X., Hospedales, T.M., Xiang, T.: Multi-level factorisation net for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  3. 3.
    Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  4. 4.
    Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: Clustering and fine-tuning. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 14(4), 83 (2018)Google Scholar
  5. 5.
    Fan, X., Luo, H., Zhang, X., He, L., Zhang, C., Jiang, W.: SCPNet: spatial-channel parallelism network for joint holistic and partial person re-identification. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11362, pp. 19–34. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-20890-5_2CrossRefGoogle Scholar
  6. 6.
    Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: ICCV. IEEE (2019)Google Scholar
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR. IEEE (2016)Google Scholar
  8. 8.
    Huang, H., et al.: Eanet: Enhancing alignment for cross-domain person re-identification. arXiv preprint arXiv:1812.11369 (2018)
  9. 9.
    Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  10. 10.
    Jiao, J., Zheng, W.S., Wu, A., Zhu, X., Gong, S.: Deep low-resolution person re-identification. In: AAAI (2018)Google Scholar
  11. 11.
    Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  12. 12.
    Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)Google Scholar
  13. 13.
    Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  14. 14.
    Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. arXiv preprint arXiv:1603.04779 (2016)
  15. 15.
    Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2018)CrossRefGoogle Scholar
  16. 16.
    Lin, S., Li, H., Li, C.T., Kot, A.C.: Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. In: BMVC (2018)Google Scholar
  17. 17.
    Lin, Y., Dong, X., Zheng, L., Yan, Y., Yang, Y.: A bottom-up clustering approach to unsupervised person re-identification. In: AAAI (2019)Google Scholar
  18. 18.
    Lin, Y., Xie, L., Wu, Y., Yan, C., Tian, Q.: Unsupervised person re-identification via softened similarity learning. In: CVPR. IEEE (2020)Google Scholar
  19. 19.
    Liu, H., Feng, J., Qi, M., Jiang, J., Yan, S.: End-to-end comparative attention networks for person re-identification. IEEE Trans. Image Process. 26(7), 3492–3506 (2017)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Liu, J., Ni, B., Yan, Y., Zhou, P., Cheng, S., Hu, J.: Pose transferrable person re-identification. In: CVPR. IEEE (2018)Google Scholar
  21. 21.
    Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPRW. IEEE (2019)Google Scholar
  22. 22.
    Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_8CrossRefGoogle Scholar
  23. 23.
    Mao, S., Zhang, S., Yang, M.: Resolution-invariant person re-identification. arXiv preprint arXiv:1906.09748 (2019)
  24. 24.
    Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: ICCV. IEEE (2019)Google Scholar
  25. 25.
    Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 484–500. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01225-0_29CrossRefGoogle Scholar
  26. 26.
    Peng, P., et al.: Unsupervised cross-dataset transfer learning for person re-identification. In: CVPR. IEEE (2016)Google Scholar
  27. 27.
    Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999)CrossRefGoogle Scholar
  28. 28.
    Rannen, A., Aljundi, R., Blaschko, M.B., Tuytelaars, T.: Encoder based lifelong learning. In: ICCV. IEEE (2017)Google Scholar
  29. 29.
    Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: CVPR. IEEE (2018)Google Scholar
  30. 30.
    Shen, Y., Li, H., Yi, S., Chen, D., Wang, X.: Person re-identification with deep similarity-guided graph neural network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 508–526. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01267-0_30CrossRefGoogle Scholar
  31. 31.
    Song, C., Huang, Y., Ouyang, W., Wang, L.: Mask-guided contrastive attention model for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  32. 32.
    Song, J., Yang, Y., Song, Y.Z., Xiang, T., Hospedales, T.M.: Generalizable person re-identification by domain-invariant mapping network. In: CVPR. IEEE (2019)Google Scholar
  33. 33.
    Song, L., et al.: Unsupervised domain adaptive re-identification: theory and practice. Pattern Recogn. (2020)Google Scholar
  34. 34.
    Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K.M.: Part-aligned bilinear representations for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 418–437. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_25CrossRefGoogle Scholar
  35. 35.
    Sun, H., Chen, Z., Yan, S., Xu, L.: MVP matching: a maximum-value perfect matching for mining hard samples, with application to person re-identification. In: ICCV. IEEE (2019)Google Scholar
  36. 36.
    Sun, Y., Zheng, L., Deng, W., Wang, S.: Svdnet for pedestrian retrieval. In: ICCV. IEEE (2017)Google Scholar
  37. 37.
    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: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 501–518. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01225-0_30CrossRefGoogle Scholar
  38. 38.
    Tian, M., et al.: Eliminating background-bias for robust person re-identification. In: CVPR. IEEE (2018)Google Scholar
  39. 39.
    Van Der Maaten, L.: Accelerating t-SNE using tree-based algorithms. JMLR 15(1), 3221–3245 (2014)MathSciNetzbMATHGoogle Scholar
  40. 40.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR. IEEE (2018)Google Scholar
  41. 41.
    Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  42. 42.
    Wei, L., Zhang, S., Yao, H., Gao, W., Tian, Q.: Glad: global-local-alignment descriptor for pedestrian retrieval. In: ACMMM. ACM (2017)Google Scholar
  43. 43.
    Wu, A., Zheng, W.S., Guo, X., Lai, J.H.: Distilled person re-identification: towards a more scalable system. In: CVPR. IEEE (2019)Google Scholar
  44. 44.
    Wu, A., Zheng, W.S., Lai, J.H.: Unsupervised person re-identification by camera-aware similarity consistency learning. In: ICCV. IEEE (2019)Google Scholar
  45. 45.
    Yu, H.X., Wu, A., Zheng, W.S.: Cross-view asymmetric metric learning for unsupervised person re-identification. In: ICCV. IEEE (2017)Google Scholar
  46. 46.
    Yu, H.X., Wu, A., Zheng, W.S.: Unsupervised person re-identification by deep asymmetric metric embedding. TPAMI (2018)Google Scholar
  47. 47.
    Yu, H.X., Zheng, W.S., Wu, A., Guo, X., Gong, S., Lai, J.H.: Unsupervised person re-identification by soft multilabel learning. In: CVPR (2019)Google Scholar
  48. 48.
    Zhang, T., Xie, L., Wei, L., Zhang, Y., Li, B., Tian, Q.: Single camera training for person re-identification. In: AAAI (2020)Google Scholar
  49. 49.
    Zhang, X., et al.: Alignedreid: surpassing human-level performance in person re-identification. arXiv preprint arXiv:1711.08184 (2017)
  50. 50.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV. IEEE (2015)Google Scholar
  51. 51.
    Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person reidentification. ACM Trans. Multimedia Comput. Commun. Appl. 14(1), 13 (2017)Google Scholar
  52. 52.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV. IEEE (2017)Google Scholar
  53. 53.
    Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR. IEEE (2017)Google Scholar
  54. 54.
    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI (2020)Google Scholar
  55. 55.
    Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero- and homogeneously. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 176–192. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_11CrossRefGoogle Scholar
  56. 56.
    Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: CVPR. IEEE (2019)Google Scholar
  57. 57.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: CVPR. IEEE (2018)Google Scholar
  58. 58.
    Zhou, J., Yu, P., Tang, W., Wu, Y.: Efficient online local metric adaptation via negative samples for person reidentification. In: ICCV. IEEE (2017)Google Scholar
  59. 59.
    Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV. IEEE (2019)Google Scholar
  60. 60.
    Zhu, X., Zhu, X., Li, M., Murino, V., Gong, S.: Intra-camera supervised person re-identification: a new benchmark. In: ICCVW. IEEE (2019)Google Scholar
  61. 61.
    Zhu, Z., et al.: Viewpoint-aware loss with angular regularization for person re-identification. In: AAAI (2020)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Tsinghua UniversityBeijingChina
  2. 2.Huawei Inc.ShenzhenChina
  3. 3.Hefei University of TechnologyHefeiChina
  4. 4.University of Science and Technology of ChinaHefeiChina

Personalised recommendations