Skip to main content
Springer Nature Link
Log in

A domain generalization pedestrian re-identification algorithm based on meta-graph aware

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Domain generalization is a key problem to solve the difference between the source domain and the target domain. This paper proposes a person re-identification algorithm based on meta-graph aware (Meta-GA) under the framework of meta-learning, which includes two stages: meta-global aware (M-GA) and meta-graph relationship sampling (M-GRS). In order to reduce inter-domain differences, a meta-global aware mechanism is proposed to construct an interaction model (paired relationship) in the meta training domain by stacking affinity models and dividing saliency features between the pedestrians. Then a learning interaction model is used to construct a global knowledge map to classify and weighted the structural information. In order to accurately learn the discriminative features, a meta-graph relationship sampling model is proposed. The similarity of the pedestrian cross-domain features between the domains is used to construct a feature relationship map between the adjacent classes. To enhance domain invariant features and improve the model generalization, positive samples are sampled cyclically and negative samples are sampled randomly. On this basis, the gradient norm is trimmed to prevent the model overfitting. The experimental results show that the robustness and accuracy of the proposed algorithm have been significantly improved. In the Market-1501 to DukeMTMC-ReID experiment, Rank-1 and mAP increased by 5.25% and 3.73%, respectively. In the DukeMTMC-ReID to Market-1501 experiment, Rank-1 and mAP increased by 1.73% and 0.93%, respectively, which are significantly superior to those of the recent representative algorithms.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig.1
Fig.2
Fig.3
Fig.4
Algorithm 1
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data availability

The datasets generated during and/or analysed during the current study are not publicly available due [REASON(S) WHY DATA ARE NOT PUBLIC] but are available from the corresponding author on reasonable request.].

References

  1. Wen-Qi L, Guang-Cong W, Jian-Huang L (2022) Asymmetric cross-domain transfer learning of person re-identification based on the many-to-many generative adversarial network. Acta Automatica Sinica 48(1):103–120

    Google Scholar 

  2. Fang W, Yi W, Pang L et al (2022) Study of cross-domain person re-identification based on DCGAN[J]. Multimedia Tools App 81(25):36551–36565

    Article  Google Scholar 

  3. Zhang S, Shang Z, Zhou M et al (2022) Cross-modal identity correlation mining for visible-thermal person re-identification[J]. Multimedia Tools App 81(28):39981–39994

    Article  Google Scholar 

  4. Wang H, Hu J (2019) Deep multi-task transfer network for cross domain person re-identification[J]. IEEE Access 8:5339–5348

    Article  Google Scholar 

  5. Li Y, Yao H, Xu C (2021) Intra-domain consistency enhancement for unsupervised person re-identification[J]. IEEE Trans Multimedia 24:415–425

    Article  Google Scholar 

  6. Guo Y, He H, Zhu Y, et al. (2022) Domain generalization Person Re-identification on Attention-aware multi-operation strategery[J]. arXiv preprint arXiv:2210.10409

  7. Bai Z, Wang Z, Wang J, et al. (2021) Unsupervised multi-source domain adaptation for person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 12914–12923

  8. Yang F, Zhong Z, Luo Z, et al. (2021) Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification[C]. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4855–4864

  9. Dai Y, Liu J, Sun Y, et al. (2021) Idm: An intermediate domain module for domain adaptive person re-id[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision 11864–11874

  10. Chen G, Lu Y, Lu J, et al. (2020) Deep credible metric learning for unsupervised domain adaptation person re-identification[C]. Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16, 643-659

  11. Qi L, Wang L, Shi Y, et al. (2022) A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification[J]. IEEE Transactions on Multimedia

  12. Pandey P, Raman M, Varambally S, et al. (2021) Generalization on unseen domains via inference-time label-preserving target projections[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12924–12933

  13. Zheng L, Shen L, Tian L, et al. (2015) Scalable person re-identification: A benchmark[C]. Proceedings of the IEEE international conference on computer vision 1116–1124

  14. Zheng Z, Zheng L, Yang Y. (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro[C]. Proceedings of the IEEE international conference on computer vision, 3754–3762

  15. Wei L, Zhang S, Gao W, et al. (2018) Person transfer gan to bridge domain gap for person re-identification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 79–88

  16. Wang P, Wu Q, Cao J, et al. (2019) Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 1960–1968

  17. Zhang Y, Li M, Li R, et al. (2022) Exact feature distribution matching for arbitrary style transfer and domain generalization[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 8035–8045

  18. Peng D, Lei Y, Hayat M, et al. (2022) Semantic-aware domain generalized segmentation[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2594–2605.

  19. Zhong Z, Zheng L, Luo Z, et al. (2019) Invariance matters: Exemplar memory for domain adaptive person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 598–607

  20. Wang Y, Li H, Chau L-P, et al. (2021) Embracing the dark knowledge: Domain generalization using regularized knowledge distillation[C]. Proceedings of the 29th ACM International Conference on Multimedia 2595–2604

  21. Finn C, Rajeswaran A, Kakade S, et al. (2019) Online meta-learning[C]. International Conference on Machine Learning, 1920–1930

  22. Wang H, Mai H, Gong Y et al (2023) Towards well-generalizing meta-learning via adversarial task augmentation[J]. Artif Intell 317:103875

    Article  MathSciNet  Google Scholar 

  23. Zhang J, Qi L, Shi Y, et al. (2022) MVDG: A Unified Multi-view Framework for Domain Generalization[C]. Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXVII, 161-177

  24. Chen K, Zhuang D, Chang JM (2022) Discriminative adversarial domain generalization with meta-learning based cross-domain validation[J]. Neurocomputing 467:418–426

    Article  Google Scholar 

  25. Xu J, Song J, Sang Y, et al. (2022) CDAML: a cluster-based domain adaptive meta-learning model for cross domain recommendation[J]. World Wide Web 1–15

  26. Wang W, Duan L, Wang Y, et al. (2022) Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 7065–7074

  27. Gong X, Yao Z, Li X et al (2021) Lag-net: Multi-granularity network for person re-identification via local attention system[J]. IEEE Trans Multimedia 24:217–229

    Article  Google Scholar 

  28. Wang P, Wu Q, Cao J, et al. (2019) Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 1960–1968

  29. Guo C, Fan B, Gu J, et al. (2019) Progressive sparse local attention for video object detection[C]. Proceedings of the IEEE/CVF International Conference on Computer Vision, 3909–3918

  30. Zhang Z, Zhang H, Liu S. (2021) Person re-identification using heterogeneous local graph attention networks[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12136–12145

  31. Zhou C, Yang G, Lu Z, et al. (2022) A noise-robust feature fusion model combining non-local attention for material recognition[C]. 2022 the 5th Int Conference Image Graphics Process (ICIGP). 132–138

  32. Wang X, Girshick R, Gupta A, et al. (2018) Non-local neural networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 7794–7803

  33. Wan Q, Wang A, Zhang G et al (2022) Discriminative and efficient non-local attention network for league of legends highlight detection[J]. Complex Intell Syst 8(6):5377–5386

    Article  Google Scholar 

  34. Yu J, Liu J, Bo L, et al. (2022) Memory-augmented non-local attention for video super-resolution[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 17834–17843

  35. Zhang Z, Lan C, Zeng W, et al. (2020) Relation-aware global attention for person re-identification[C]//Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 3186–3195

  36. Choi S, Kim T, Jeong M, et al. (2021) Meta batch-instance normalization for generalizable person re-identification[C]. Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition 3425–3435

  37. He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778

  38. Deng W, Zheng L, Ye Q, et al. (2018) Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 994–1003

  39. Zhong Z, Zheng L, Zheng Z et al (2018) Camstyle: A novel data augmentation method for person re-identification[J]. IEEE Trans Image Process 28(3):1176–1190

    Article  MathSciNet  Google Scholar 

  40. Qi L, Wang L, Huo J, et al. (2019) A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]. Proceedings of the IEEE/CVF international conference on computer vision, 8080–8089

  41. Lin Y, Dong X, Zheng L, et al. (2019) A bottom-up clustering approach to unsupervised person re-identification[C]. Proc AAAI Conference on Artificial Intell 8738–8745

  42. Fan H, Zheng L, Yan C, et al (2018) Unsupervised person re-identification Clustering and fine-tuning[J]. ACM Trans Multimedia Comp Commun App (TOMM) 14(4): 1–18

  43. Zhang T, Xie L, Wei L, et al. (2021) Unrealperson: An adaptive pipeline towards costless person re-identification[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11506–11515

  44. Liao S, Shao L. (2020) Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting[C]. European Conference on Computer Vision, 456–474

Download references

Acknowledgements

The authors thank the anonymous reviewers and editors for the very constructive comments. This work was supported by the National Natural Science Foundation of China (61962046, 62262048, 62001255, 62066036, 61841204); Inner Mongolia Science and Technology Plan Project (2020GG0315, 2021GG0082); Inner Mongolia Natural Science Foundation (2022MS06017, 2019MS06003, 2018MS06018); The Central Government Guides Local Science and Technology Development Fund Project of China (grant number: 2021ZY0004); Inner Mongolia College Science and Technology Research Project (grant numbers: NJZY145); Chunhui Program of the Ministry of Education of the People’s Republic of China (1383). Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region (grant number: NJYT23057); Fundamental Research Funds for Inner Mongolia University of Science & Technology (grant number: 019, 042).

Author information

Author notes

  1. Dongyang Wu, Baohua Zhang, Xiaoqi Lu, Yongxiang Li, Yu Gu, Jianjun Li and Guoyin Ren contributed equally to this work. 

Authors and Affiliations

  1. School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou, 014010, Inner Mongolia, China

    Dongyang Wu, Baohua Zhang, Yu Gu, Jianjun Li & Guoyin Ren

  2. School of Information Engineering, Mongolia Industrial University, Huhehaote, 010051, Inner Mongolia, China

    Xiaoqi Lu

  3. College of Energy and Transportation Engineering, Inner Mongolia Agricultural University, Huhehaote, 010051, Inner Mongolia, China

    Yongxiang Li & Jianjun Li

Authors
  1. Dongyang Wu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Baohua Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Xiaoqi Lu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yongxiang Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Yu Gu
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Jianjun Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Guoyin Ren
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Dongyang Wu or Baohua Zhang.

Ethics declarations

Conflict of interest

All authors of this manuscript have directly participated in planning, execution, and/or analysis of this study (if not,specify).

The contents of this manuscript have not been copyrighted or published previously.

The contents of this manuscript are not now under consideration for publication elsewhere.

There are no directly related manuscripts or abstracts, published or unpublished, by any authors of this manuscript.

No financial support or incentive has been provided for this manuscript.

I am one author signing on behalf of all co-authors of this manuscript, and attesting to the above.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, D., Zhang, B., Lu, X. et al. A domain generalization pedestrian re-identification algorithm based on meta-graph aware. Multimed Tools Appl 83, 2913–2933 (2024). https://doi.org/10.1007/s11042-023-15765-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15765-4

Keywords