Advertisement

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12347)

Abstract

Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in using unsupervised domain adaptation to address this scalability issue. Existing methods typically conduct adaptation on the representation space that contains both id-related and id-unrelated factors, thus inevitably undermining the adaptation efficacy of id-related features. In this paper, we seek to improve adaptation by purifying the representation space to be adapted. To this end, we propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively. Our model involves a disentangling module that encodes cross-domain images into a shared appearance space and two separate structure spaces, and an adaptation module that performs adversarial alignment and self-training on the shared appearance space. The two modules are co-designed to be mutually beneficial. Extensive experiments demonstrate that the proposed joint learning framework outperforms the state-of-the-art methods by clear margins.

Keywords

Person re-id Feature disentangling Domain adaptation 

Supplementary material

504434_1_En_6_MOESM1_ESM.pdf (433 kb)
Supplementary material 1 (pdf 433 KB)

References

  1. 1.
    Chen, B., et al.: Angular visual hardness. In: ICML (2020)Google Scholar
  2. 2.
    Chen, W., Yu, Z., Wang, Z., Anandkumar, A.: Automated synthetic-to-real generalization. In: ICML (2020)Google Scholar
  3. 3.
    Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: NeurIPS (2016)Google Scholar
  4. 4.
    Chen, Y., Zhu, X., Gong, S.: Instance-guided context rendering for cross-domain person re-identification. In: ICCV (2019)Google Scholar
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  6. 6.
    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 (2018)Google Scholar
  7. 7.
    Dundar, A., Liu, M.Y., Yu, Z., Wang, T.C., Zedlewski, J., Kautz, J.: Domain stylization: a fast covariance matching framework towards domain adaptation. In: TPAMI (2020)Google Scholar
  8. 8.
    Eom, C., Ham, B.: Learning disentangled representation for robust person re-identification. In: NeurIPS (2019)Google Scholar
  9. 9.
    Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD (1996)Google Scholar
  10. 10.
    Fan, L., Li, T., Fang, R., Hristov, R., Yuan, Y., Katabi, D.: Learning longterm representations for person re-identification using radio signals. In: CVPR (2020)Google Scholar
  11. 11.
    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 (2019)Google Scholar
  12. 12.
    Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: ICLR (2020)Google Scholar
  13. 13.
    Ge, Y., Li, Z., Zhao, H., Yin, G., Yi, S., Wang, X., et al.: FD-GAN: pose-guided feature distilling GAN for robust person re-identification. In: NeurIPS (2018)Google Scholar
  14. 14.
    Hadad, N., Wolf, L., Shahar, M.: A two-step disentanglement method. In: CVPR (2018)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  16. 16.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv arXiv:1703.07737 (2017)
  17. 17.
    Higgins, I., et al.: \(\beta \)-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)Google Scholar
  18. 18.
    Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: ICML (2018)Google Scholar
  19. 19.
    Hong, W., Wang, Z., Yang, M., Yuan, J.: Conditional generative adversarial network for structured domain adaptation. In: CVPR (2018)Google Scholar
  20. 20.
    Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV (2017)Google Scholar
  21. 21.
    Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179–196. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_11CrossRefGoogle Scholar
  22. 22.
    Huang, Y., Xu, J., Wu, Q., Zheng, Z., Zhang, Z., Zhang, J.: Multi-pseudo regularized label for generated data in person re-identification. TIP 28, 1391–1403 (2019)MathSciNetGoogle Scholar
  23. 23.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)Google Scholar
  24. 24.
    Kalayeh, M., Basaran, E., Muhittin Gokmen, M.K., Shah, M.: Human semantic parsing for person re-identification. In: CVPR (2018)Google Scholar
  25. 25.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  26. 26.
    Lee, C.Y., Batra, T., Baig, M.H., Ulbricht, D.: Sliced Wasserstein discrepancy for unsupervised domain adaptation. In: CVPR (2019)Google Scholar
  27. 27.
    Lee, H.Y., Tseng, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Diverse image-to-image translation via disentangled representations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205. Springer, Cham (2018)CrossRefGoogle Scholar
  28. 28.
    Li, Y.J., Lin, C.S., Lin, Y.B., Wang, Y.C.: Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: ICCV (2019)Google Scholar
  29. 29.
    Li, Y.J., Yang, F.E., Liu, Y.C., Yeh, Y.Y., Du, X., Wang, Y.C.: Adaptation and re-identification network: an unsupervised deep transfer learning approach to person re-identification. In: CVPR Workshop (2018)Google Scholar
  30. 30.
    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
  31. 31.
    Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: CVPR (2019)Google Scholar
  32. 32.
    Liu, J., Ni, B., Yan, Y., Zhou, P., Cheng, S., Hu, J.: Pose transferrable person re-identification. In: CVPR (2018)Google Scholar
  33. 33.
    Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  34. 34.
    Mathieu, M.F., Zhao, J.J., Zhao, J., Ramesh, A., Sprechmann, P., LeCun, Y.: Disentangling factors of variation in deep representation using adversarial training. In: NeurIPS (2016)Google Scholar
  35. 35.
    Naphade, M., et al.: The 4th AI city challenge. In: CVPR Workshop (2020)Google Scholar
  36. 36.
    Qi, L., Wang, L., Huo, J., Zhou, L., Shi, Y., Gao, Y.: A novel unsupervised camera-aware domain adaptation framework for person re-identification. In: ICCV (2019)Google Scholar
  37. 37.
    Qian, X., et al.: Pose-normalized image generation for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01240-3_40CrossRefGoogle Scholar
  38. 38.
    Ren, C.X., Liang, B.H., Lei, Z.: Domain adaptive person re-identification via camera style generation and label propagation. arXiv arXiv:1905.05382 (2019)
  39. 39.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV Workshop (2016)Google Scholar
  40. 40.
    Song, L., et al.: Unsupervised domain adaptive re-identification: Theory and practice. arXiv arXiv:1807.11334 (2018)
  41. 41.
    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
  42. 42.
    Su, C., Zhang, S., Xing, J., Gao, W., Tian, Q.: Deep attributes driven multi-camera person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_30CrossRefGoogle Scholar
  43. 43.
    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.) ECCV 2018. LNCS, vol. 11218, pp. 418–437. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_25CrossRefGoogle Scholar
  44. 44.
    Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49409-8_35CrossRefGoogle Scholar
  45. 45.
    Sun, Y., Zheng, L., Deng, W., Wang, S.: SVDNet for pedestrian retrieval. In: ICCV (2017)Google Scholar
  46. 46.
    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. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01225-0_30CrossRefGoogle Scholar
  47. 47.
    Tang, Z., et al.: PAMTRI: Pose-aware multi-task learning for vehicle re-identification using randomized synthetic data. In: ICCV (2019)Google Scholar
  48. 48.
    Tang, Z., et al.: CityFlow: a city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification. In: CVPR (2019)Google Scholar
  49. 49.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  50. 50.
    Wang, C., Zhang, Q., Huang, C., Liu, W., Wang, X.: Mancs: a multi-task attentional network with curriculum sampling for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01225-0_23CrossRefGoogle Scholar
  51. 51.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR (2018)Google Scholar
  52. 52.
    Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)Google Scholar
  53. 53.
    Wei, L., Zhang, S., Yao, H., Gao, W., Tian, Q.: GLAD: global-local-alignment descriptor for pedestrian retrieval. In: ACM Multimedia (2017)Google Scholar
  54. 54.
    Yang, Q., Yu, H.X., Wu, A., Zheng, W.S.: Patch-based discriminative feature learning for unsupervised person re-identification. In: CVPR (2019)Google Scholar
  55. 55.
    Yao, Y., Zheng, L., Yang, X., Naphade, M., Gedeon, T.: Simulating content consistent vehicle datasets with attribute descent. In: ECCV (2020, to appear) Google Scholar
  56. 56.
    Zhao, H., et al.: Spindle Net: person re-identification with human body region guided feature decomposition and fusion. In: CVPR (2017)Google Scholar
  57. 57.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)Google Scholar
  58. 58.
    Zheng, M., Karanam, S., Wu, Z., Radke, R.: Re-identification with consistent attentive Siamese networks. In: CVPR (2019)Google Scholar
  59. 59.
    Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: CVPR (2019)Google Scholar
  60. 60.
    Zheng, Z., Yang, Y.: Person re-identification in the 3D space. arXiv arXiv:2006.04569 (2020)
  61. 61.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)Google Scholar
  62. 62.
    Zheng, Z., Zheng, L., Yang, Y.: Pedestrian alignment network for large-scale person re-identification. In: TCSVT (2018)Google Scholar
  63. 63.
    Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR (2017)Google Scholar
  64. 64.
    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
  65. 65.
    Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: CVPR (2019)Google Scholar
  66. 66.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)Google Scholar
  67. 67.
    Zou, Y., Yu, Z., Vijaya Kumar, B.V.K., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 297–313. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_18CrossRefGoogle Scholar
  68. 68.
    Zou, Y., Yu, Z., Liu, X., Kumar, B.V., Wang, J.: Confidence regularized self-training. In: ICCV (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.NVIDIASanta ClaraUSA

Personalised recommendations