Advertisement

Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12360)

Abstract

Despite the impressive performance under the single-domain setup, current fully-supervised models for person re-identification (re-ID) degrade significantly when deployed to an unseen domain. According to the characteristics of cross-domain re-ID, such degradation is mainly attributed to the dramatic variation within the target domain and the severe shift between the source and target domain. To achieve a model that generalizes well to the target domain, it is desirable to take both issues into account. In terms of the former issue, one of the most successful solutions is to enforce consistency between nearest-neighbors in the embedding space. However, we find that the search of neighbors is highly biased due to the discrepancy across cameras. To this end, we improve the vanilla neighborhood invariance approach by imposing the constraint in a camera-aware manner. As for the latter issue, we propose a novel cross-domain mixup scheme. It alleviates the abrupt transfer by introducing the interpolation between the two domains as a transition state. Extensive experiments on three public benchmarks demonstrate the superiority of our method. Without any auxiliary data or models, it outperforms existing state-of-the-arts by a large margin. The code is available at https://github.com/LuckyDC/generalizing-reid.

Keywords

Domain adaptation Person re-identification Camera-aware invariance learning Cross-domain mixup 

Notes

Acknowledgement

This work was supported in part by the National Key R&D Program of China (No. 2018YFB1004602), the National Natural Science Foundation of China (No. 61836014, No. 61761146004, No. 61773375).

Supplementary material

504470_1_En_14_MOESM1_ESM.pdf (384 kb)
Supplementary material 1 (pdf 384 KB)

References

  1. 1.
    Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.: Mixmatch: a holistic approach to semi-supervised learning. arXiv:1905.02249 (2019)
  2. 2.
    Chen, B., Deng, W., Shen, H.: Virtual class enhanced discriminative embedding learning. In: NeurIPS (2018)Google Scholar
  3. 3.
    Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: CVPR (2017)Google Scholar
  4. 4.
    Chen, Y., Zhu, X., Gong, S.: Deep association learning for unsupervised video person re-identification. In: BMVC (2018)Google Scholar
  5. 5.
    Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: NeurIPS (2017)Google Scholar
  6. 6.
    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
  7. 7.
    Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: CVPR (2018)Google Scholar
  8. 8.
    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
  9. 9.
    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
  10. 10.
    Ding, Y., Fan, H., Xu, M., Yang, Y.: Adaptive exploration for unsupervised person re-identification. arXiv:1907.04194 (2019)
  11. 11.
    Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. ACM Trans. Multimed. Comput. Commun. Appl. 14, 83 (2018)CrossRefGoogle Scholar
  12. 12.
    Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.: Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: ICCV (2019)Google Scholar
  13. 13.
    Fu, Y., et al.: Horizontal pyramid matching for person re-identification. In: AAAI (2019)Google Scholar
  14. 14.
    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
  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:1703.07737 (2017)
  17. 17.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)Google Scholar
  18. 18.
    Huang, H., et al.: Eanet: enhancing alignment for cross-domain person re-identification. arXiv:1812.11369 (2018)
  19. 19.
    Huang, Y., Wu, Q., Xu, J., Zhong, Y.: Sbsgan: suppression of inter-domain background shift for person re-identification. In: ICCV (2019)Google Scholar
  20. 20.
    Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: CVPR (2018)Google Scholar
  21. 21.
    Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)Google Scholar
  22. 22.
    Li, K., Ding, Z., Li, K., Zhang, Y., Fu, Y.: Support neighbor loss for person re-identification. In: ACM MM (2018)Google Scholar
  23. 23.
    Li, M., Zhu, X., Gong, S.: Unsupervised person re-identification by deep learning tracklet association. In: ECCV (2018)Google Scholar
  24. 24.
    Li, Y.J., Yang, F.E., Liu, Y.C., Yeh, Y.Y., Du, X., Frank Wang, Y.C.: Adaptation and re-identification network: an unsupervised deep transfer learning approach to person re-identification. In: CVPR Workshop (2018)Google Scholar
  25. 25.
    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
  26. 26.
    Mao, X., Ma, Y., Yang, Z., Chen, Y., Li, Q.: Virtual mixup training for unsupervised domain adaptation. arXiv:1905.04215 (2019)
  27. 27.
    Paszke, A., et al.: Automatic differentiation in pytorch. In: NeurIPS Workshop (2017)Google Scholar
  28. 28.
    Quan, R., Dong, X., Wu, Y., Zhu, L., Yang, Y.: Auto-reid: searching for a part-aware convnet for person re-identification. In: ICCV (2019)Google Scholar
  29. 29.
    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).  https://doi.org/10.1007/978-3-319-48881-3_2CrossRefGoogle Scholar
  30. 30.
    Rukhovich, D., Galeev, D.: Mixmatch domain adaptaion: Prize-winning solution for both tracks of visda 2019 challenge. arXiv:1910.03903 (2019)
  31. 31.
    Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR (2015)Google Scholar
  32. 32.
    Song, L., et al.: Unsupervised domain adaptive re-identification: theory and practice. arXiv:1807.11334 (2018)
  33. 33.
    Suh, Y., Wang, J., Tang, S., Mei, T., Mu Lee, K.: Part-aligned bilinear representations for person re-identification. In: ECCV (2018)Google Scholar
  34. 34.
    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: ECCV (2018)Google Scholar
  35. 35.
    Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: ICML (2019)Google Scholar
  36. 36.
    Verma, V., Lamb, A., Kannala, J., Bengio, Y., Lopez-Paz, D.: Interpolation consistency training for semi-supervised learning. arXiv:1903.03825 (2019)
  37. 37.
    Wang, C., Zhang, Q., Huang, C., Liu, W., Wang, X.: Mancs: a multi-task attentional network with curriculum sampling for person re-identification. In: ECCV (2018)Google Scholar
  38. 38.
    Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: ACM MM (2018)Google Scholar
  39. 39.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR (2018)Google Scholar
  40. 40.
    Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)Google Scholar
  41. 41.
    Wu, A., Zheng, W.S., Lai, J.H.: Unsupervised person re-identification by camera-aware similarity consistency learning. In: ICCV (2019)Google Scholar
  42. 42.
    Wu, J., et al.: Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification. In: ICME (2019)Google Scholar
  43. 43.
    Wu, J., Yang, Y., Liu, H., Liao, S., Lei, Z., Li, S.Z.: Unsupervised graph association for person re-identification. In: ICCV (2019)Google Scholar
  44. 44.
    Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)Google Scholar
  45. 45.
    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
  46. 46.
    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
  47. 47.
    Yu, R., Dou, Z., Bai, S., Zhang, Z., Xu, Y., Bai, X.: Hard-aware point-to-set deep metric for person re-identification. In: ECCV (2018)Google Scholar
  48. 48.
    Zhai, Y., Guo, X., Lu, Y., Li, H.: In defense of the classification loss for person re-identification. In: CVPR Workshops (2019)Google Scholar
  49. 49.
    Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)Google Scholar
  50. 50.
    Zhang, X., Cao, J., Shen, C., You, M.: Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: ICCV (2019)Google Scholar
  51. 51.
    Zhang, Z., Lan, C., Zeng, W., Chen, Z.: Densely semantically aligned person re-identification. In: CVPR (2019)Google Scholar
  52. 52.
    Zheng, F., et al.: Pyramidal person re-identification via multi-loss dynamic training. In: CVPR (2019)Google Scholar
  53. 53.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)Google Scholar
  54. 54.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)Google Scholar
  55. 55.
    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. arXiv:1708.04896 (2017)
  56. 56.
    Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero-and homogeneously. In: ECCV (2018)Google Scholar
  57. 57.
    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
  58. 58.
    Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Learning to adapt invariance in memory for person re-identification. arXiv:1908.00485 (2019)
  59. 59.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camstyle: a novel data augmentation method for person re-identification. IEEE Trans. Image Process. 28, 1176–1190 (2019)MathSciNetCrossRefGoogle Scholar
  60. 60.
    Zhong, Z., Zhu, L., Luo, Z., Li, S., Yang, Y., Sebe, N.: Openmix: reviving known knowledge for discovering novel visual categories in an open world. arXiv:2004.05551 (2020)
  61. 61.
    Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV (2019)Google Scholar
  62. 62.
    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
  63. 63.
    Zhu, X., Zhu, X., Li, M., Murino, V., Gong, S.: Intra-camera supervised person re-identification: a new benchmark. In: ICCV Workshop (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of Chinese Academy of SciencesBeijingChina
  2. 2.Center for Research on Intelligent Perception and Computing, NLPR, CASIABeijingChina
  3. 3.Center for Excellence in Brain Science and Intelligence Technology, CAS ShanghaiChina

Personalised recommendations