Skip to main content

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time, which is a realistic but challenging problem. In contrast to methods assuming an identical model for different domains, Mixture of Experts (MoE) exploits multiple domain-specific networks for leveraging complementary information between domains, obtaining impressive results. However, prior MoE-based DG ReID methods suffer from a large model size with the increase of the number of source domains, and most of them overlook the exploitation of domain-invariant characteristics. To handle the two issues above, this paper presents a new approach called Mimic Embedding via adapTive Aggregation (\(\textsf{META}\)) for DG person ReID. To avoid the large model size, experts in \(\textsf{META}\) do not adopt a branch network for each source domain but share all the parameters except for the batch normalization layers. Besides multiple experts, \(\textsf{META}\) leverages Instance Normalization (IN) and introduces it into a global branch to pursue invariant features across domains. Meanwhile, \(\textsf{META}\) considers the relevance of an unseen target sample and source domains via normalization statistics and develops an aggregation module to adaptively integrate multiple experts for mimicking unseen target domain. Benefiting from a proposed consistency loss and an episodic training algorithm, \(\textsf{META}\) is expected to mimic embedding for a truly unseen target domain. Extensive experiments verify that \(\textsf{META}\) surpasses state-of-the-art DG person ReID methods by a large margin. Our code is available at https://github.com/xbq1994/META.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bai, Y., et al.: Person30k: a dual-meta generalization network for person re-identification. In: CVPR (2021)

    Google Scholar 

  2. Bai, Z., Wang, Z., Wang, J., Hu, D., Ding, E.: Unsupervised multi-source domain adaptation for person re-identification. In: CVPR (2021)

    Google Scholar 

  3. Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: CVPR (2019)

    Google Scholar 

  4. Choi, S., Kim, T., Jeong, M., Park, H., Kim, C.: Meta batch-instance normalization for generalizable person re-identification. In: CVPR (2021)

    Google Scholar 

  5. Dai, Y., Li, X., Liu, J., Tong, Z., Duan, L.Y.: Generalizable person re-identification with relevance-aware mixture of experts. In: CVPR (2021)

    Google Scholar 

  6. Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. arXiv (2016)

    Google Scholar 

  7. 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 

  8. Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: ECCV (2008)

    Google Scholar 

  9. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  10. He, L., Liang, J., Li, H., Sun, Z.: Deep spatial feature reconstruction for partial person re-identification: alignment-free approach. In: CVPR (2018)

    Google Scholar 

  11. He, L., et al.: Semi-supervised domain generalizable person re-identification. arXiv (2021)

    Google Scholar 

  12. Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv (2017)

    Google Scholar 

  13. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS (2017)

    Google Scholar 

  14. Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Scandinavian Conference on Image Analysis (2011)

    Google Scholar 

  15. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)

    Google Scholar 

  16. Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Computat. 3(1), 79–87 (1991)

    Article  Google Scholar 

  17. Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: CVPR (2020)

    Google Scholar 

  18. Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)

    Google Scholar 

  19. Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y.Z., Hospedales, T.M.: Episodic training for domain generalization. In: ICCV (2019)

    Google Scholar 

  20. Li, W., Wang, X.: Locally aligned feature transforms across views. In: CVPR (2013)

    Google Scholar 

  21. Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: CVPR (2014)

    Google Scholar 

  22. Liao, S., Shao, L.: Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In: ECCV (2020)

    Google Scholar 

  23. Liu, J., Ni, B., Yan, Y., Zhou, P., Cheng, S., Hu, J.: Pose transferrable person re-identification. In: CVPR (2018)

    Google Scholar 

  24. Liu, Q., Dou, Q., Yu, L., Heng, P.A.: Ms-Net: multi-site network for improving prostate segmentation with heterogeneous MRI data. IEEE Trans. Med. Imaging 39(9), 2713–2724 (2020)

    Article  Google Scholar 

  25. Liu, X., Zhang, P., Yu, C., Lu, H., Yang, X.: Watching you: global-guided reciprocal learning for video-based person re-identification. In: CVPR (2021)

    Google Scholar 

  26. Loy, C.C., Xiang, T., Gong, S.: Time-delayed correlation analysis for multi-camera activity understanding. Int. J. Comput. Vis. 90(1), 106–129 (2010)

    Article  Google Scholar 

  27. Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)

    MATH  Google Scholar 

  28. Mancini, M., Bulo, S.R., Caputo, B., Ricci, E.: Robust place categorization with deep domain generalization. IEEE Roboti. Autom. Lett. 3(3), 2093–2100 (2018)

    Article  Google Scholar 

  29. Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: ICCV (2019)

    Google Scholar 

  30. Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-net. In: ECCV (2018)

    Google Scholar 

  31. Qiao, S., Liu, C., Shen, W., Yuille, A.L.: Few-shot image recognition by predicting parameters from activations. In: CVPR (2018)

    Google Scholar 

  32. Segu, M., Tonioni, A., Tombari, F.: Batch normalization embeddings for deep domain generalization. arXiv (2020)

    Google Scholar 

  33. Seo, S., Suh, Y., Kim, D., Kim, G., Han, J., Han, B.: Learning to optimize domain specific normalization for domain generalization. In: ECCV (2020)

    Google Scholar 

  34. Shankar, S., Piratla, V., Chakrabarti, S., Chaudhuri, S., Jyothi, P., Sarawagi, S.: Generalizing across domains via cross-gradient training. arXiv (2018)

    Google Scholar 

  35. Song, J., Yang, Y., Song, Y.Z., Xiang, T., Hospedales, T.M.: Generalizable person re-identification by domain-invariant mapping network. In: CVPR (2019)

    Google Scholar 

  36. 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 

  37. Sun, Y., Zheng, L., Li, Y., Yang, Y., Tian, Q., Wang, S.: Learning part-based convolutional features for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 902–917 (2019)

    Article  Google Scholar 

  38. 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 

  39. 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 

  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. Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: End-to-end deep learning for person search. arXiv (2016)

    Google Scholar 

  42. Xu, B., He, L., Liang, J., Sun, Z.: Learning feature recovery transformer for occluded person re-identification. IEEE Trans. Image Process. 31, 4651–4662 (2022)

    Article  Google Scholar 

  43. Xu, B., He, L., Liao, X., Liu, W., Sun, Z., Mei, T.: Black Re-ID: a head-shoulder descriptor for the challenging problem of person re-identification. In: ACM MM (2020)

    Google Scholar 

  44. Zhai, Y., et al.: Ad-cluster: augmented discriminative clustering for domain adaptive person re-identification. In: CVPR (2020)

    Google Scholar 

  45. Zhao, Y., et al.: Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In: CVPR (2021)

    Google Scholar 

  46. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV (2015)

    Google Scholar 

  47. Zheng, W.S., Gong, S., Xiang, T.: Associating groups of people. In: BMVC, pp. 1–11 (2009)

    Google Scholar 

  48. Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV (2017)

    Google Scholar 

  49. 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 

  50. Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization: a survey. arXiv (2021)

    Google Scholar 

Download references

Acknowledgment

The authors would like to thank reviewers for providing valuable suggestions to improve this paper. This work is supported by the National Natural Science Foundation of China (Grant No. U1836217) and the Beijing Nova Program under Grant Z211100002121108.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Zhenan Sun .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Xu, B., Liang, J., He, L., Sun, Z. (2022). Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13674. Springer, Cham. https://doi.org/10.1007/978-3-031-19781-9_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19781-9_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19780-2

  • Online ISBN: 978-3-031-19781-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics