Skip to main content
SpringerLink
Log in

Learning camera invariant deep features for semi-supervised person re-identification

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

Abstract

In this paper, we focus on the semi-supervised person re-identification (re-ID) task, where the training data includes some labeled data and most unlabeled data. Since the re-ID task is used for cross-camera scenes, learning camera invariant deep features become critical. We propose a novel end-to-end semi-supervised person re-ID method by introducing the context information, i.e., the camera information (camera ID) which could be easily collected without any manual annotation. Specifically, we design a camera-based hard triplet loss for (pseudo-) labeled data to learn the camera invariant features. The loss not only learns the similar features between the cross-camera anchor and the hard positive sample but also learns the distinguishing features between the within-camera anchor and the hard negative sample. For unlabeled data, we use both diversity loss and similarity loss to diversify unlabeled data features and mine similar samples. And we design an adaptive feature fusion module, which could adaptively combine the Global Average Pooling (GAP) and Global Max Pooling (GMP) features to learn person-specific discriminative information in a global-local manner. Furthermore, to validate the effectiveness of our approach, we conduct extensive experiments on two large-scale image re-ID datasets, including Market-1501 and DukeMTMC-reID. The experimental results demonstrate that our approach outperforms the state-of-the-art method by 4.8% on Market-1501, and 7.2% on DukeMTMC-reID.

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

Access this article

Log in via an institution

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Bak S, Carr P (2017) One-Shot Metric Learning for Person Re-identification. IEEE Conference on Computer Vision and Pattern Recogn:1571–1580

  2. Bengio Y, Louradour J, Collobert R, and Weston J (2009) "Curriculum learning," in Proceedings of International Conference on Machine Learning, pp. 1–8.

  3. Chen B, Deng W and Hu J (2019) "Mixed high-order attention network for person re-identification," in IEEE International Conference on Computer Vision, pp. 371–381.

  4. Chen G, Lin C, Ren L, Lu J and Zhou J "Self-critical attention learning for person re-identification," in IEEE International Conference on Computer Vision, 2019, pp. 9637–9646.

  5. Chen Y, Zhu X, and Gong S (2018) "Deep association learning for unsupervised video person re-identification," CoRR. abs/1808.07301

  6. Chowdhary CL (2019) 3D object recognition system based on local shape descriptors and depth data analysis. Recent Patents Comput Sci 12:18–24

    Article  Google Scholar 

  7. Das TK, Chowdhary CL, Gao XZ (2020) Chest X-ray investigation: a convolutional neural network approach. Biomimetics, Biomater Biomed Eng 45:57–70

    Article  Google Scholar 

  8. Deng J, Dong W, Socher R, Li L-J, Li K and Fei-Fei L (2009) "ImageNet: A large-scale hierarchical image database," in IEEE Conference on Computer Vision and Pattern Recognition 248–255.

  9. Deng W, Zheng L, Ye Q, Kang G, Yang Y, and Jiao J (2018) "Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification," in IEEE Conference on Computer Vision and Pattern Recognition pp. 994–1003.

  10. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32:1627–1645

    Article  Google Scholar 

  11. Fu Y, Wei Y, Zhou Y, Shi H, Huang G, and Wang X (2019) "Horizontal Pyramid Matching for Person Re-Identification," in Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8295–8302.

  12. Fu Y, Wei Y, Wang G, Zhou Y, and Shi H (2019) Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification," in IEEE International Conference on Computer Vision. pp. 6111–6120.

  13. He K, Zhang X, Ren S, and Sun J (2016) "Deep Residual Learning for Image Recognition," in IEEE Conference on Computer Vision and Pattern Recogn. 770–778.

  14. Hermans A, Beyer L, and Leibe B (2017) "In defense of the triplet loss for person re-identification," CoRR, abs/1703.07737

  15. Huang H, Yang W, Chen X, Zhao X, and Huang K (2018) "EANet: Enhancing alignment for cross-domain person re-identification," CoRR, abs/1812.11369

  16. Ioffe S, and Szegedy C (2015) "Batch normalization: Accelerating deep network training by reducing internal covariate shift," CoRR, abs/1502.03167.

  17. Iscen A, Tolias G, Avrithis Y, and Chum O (2019) "Label Propagation for Deep Semi-Supervised Learning," in IEEE Conference on Computer Vision and Pattern Recognition. 5065–5074.

  18. Khare N, Devan P, Chowdhary CL, Bhattacharya S, Singh G, Singh S, Yoon B (2020) Smo-dnn: spider monkey optimization and deep neural network hybrid classifier model for intrusion detection. Electronics 9:1–1

    Article  Google Scholar 

  19. Kumar MP, Packer B, and Koller D (2010)"Self-paced learning for latent variable models," in Advances in neural information processing systems. 1189–1197.

  20. Li W, Zhao R, Xiao T, and Wang X (2014) "DeepReID: Deep Filter Pairing Neural Network for Person Re-identification," IEEE Conf Comput Vision Pattern Recogn. 152–159.

  21. Li W, Zhu X, Gong S (2018) Harmonious Attention Network for Person Re-identification. IEEE Conf Comput Vision Pattern Recogn:2285–2294

  22. Lin M, Chen Q, and Yan S (2013) "Network in network," CoRR, abs/1312.4400,

  23. Lin Y, Dong X, Zheng L, Yan Y, and Yang Y (2019) "A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification," in Proceedings of the AAAI Conference on Artificial Intelligence. 8738–8745.

  24. Lin Y, Zheng L, Zheng Z, Wu Y, Hu Z, Yan C, Yang Y (2019) Improving person re-identification by attribute and identity learning. Pattern Recogn 95:151–161

    Article  Google Scholar 

  25. Liu C, Huynh D, Reynolds M (2019) Urban area vehicle re-identification with self-attention stair feature fusion and temporal Bayesian re-ranking. Int Joint Conf Neural Networks:1–8

  26. Liu Z, Wang D, Lu H (2017) Stepwise Metric Promotion for Unsupervised Video Person Re-identification. IEEE Int Conf Comput Vision:2448–2457

  27. Ma F, Meng D, Xie Q, Li Z, and Dong X (2017)"Self-paced co-training," in International Conference on Machine Learning pp. 2275–2284.

  28. Miao J, Wu Y, Liu P, Ding Y, and Yang Y (2019) "Pose-guided feature alignment for occluded person re-identification," in IEEE International Conference on Computer Vision pp. 542–551

  29. Modhej N, Bastanfard A, Teshnehlab M, Raiesdana S (2020) Pattern separation network based on the hippocampus activity for handwritten recognition. IEEE Access 8:212803–212817

    Article  Google Scholar 

  30. Nie J, Huang L, Zhang W, Wei G, Wei Z (2019) Deep feature ranking for person re-identification. IEEE Access 7:15007–15017

    Article  Google Scholar 

  31. Qi M, Han J, Jiang J, and Liu H (2019) "Deep feature representation and multiple metric ensembles for person re-identification in security surveillance system". Multimedia Tools Appl. 78: 27029–27043.

  32. Ristani E, Solera F, Zou R, and Cucchiara R (2016) "Performance measures and a data set for multi-target, multi-camera tracking," in European Conference on Computer Vision, pp. 17–35.

  33. Sarfraz MS, Schumann A, Eberle A, Stiefelhagen R (2018) A Pose-Sensitive Embedding for Person Re-identification with Expanded Cross Neighborhood Re-ranking. IEEE Conf Comput Vision Patt Recogn:420–429

  34. Shen Y, Xiao T, Yi S, Chen D, Wang X, Li H (2019) Person re-identification with deep Kronecker-product matching and group-shuffling random walk. IEEE Trans Pattern Anal Mach Intell 41:1–1

    Article  Google Scholar 

  35. Shi W, Gong Y, and Ding C (2018) "Transductive semi-supervised deep learning using min-max features," in Proceedings of the European Conference on Computer Vision. 299–315.

  36. Sun Y, Zheng L, Yang Y, and Tian Q (2018) "Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)," in Proceedings of the European Conference on Computer Vision 480–496.

  37. Sun Y, Xu Q, Li Y, Zhang C, Li Y, Wang S, and Sun J (2019) "Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification," in IEEE Conference on Computer Vision and Pattern Recogn, , pp. 393–402.

  38. Tang Z, Naphade M, Liu MY, Yang X, Birchfield S, Wang S, and Hwang JN (2019) "Cityflow: A city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification," in IEEE Conference on Computer Vision and Pattern Recognition .8797–8806

  39. Wang GA, Yang S, Liu H, Wang Z, Yang Y, Wang S, and Sun J (2020) "High-order information matters: Learning relation and topology for occluded person re-identification," in IEEE Conference on Computer Vision and Pattern Recognition . 6449–6458.

  40. Wei L, Zhang S, Gao W, and Tian Q (2018) "Person Transfer GAN to Bridge Domain Gap for Person Re-identification," in IEEE Conference on Computer Vision and Pattern Recogn. 79–88.

  41. Wu Y, Lin Y, Dong X, Yan Y, Bian W, Yang Y (2019) Progressive learning for person re-identification with one example. IEEE Trans Image Process 28:2872–2881

    Article  MathSciNet  Google Scholar 

  42. Xiang S, Fu Y, Chen H, Ran W, Liu T (2020) Multi-level feature learning with attention for person re-identification. Multimed Tools Appl 79:32079–32093

    Article  Google Scholar 

  43. Ye M, Ma AJ, Zheng L, Li J, Yuen PC (2017) Dynamic Label Graph Matching for Unsupervised Video Re-identification. IEEE Int Conf Comput Vision:5152–5160

  44. Yi D, Lei Z, Liao S, and Li SZ (2014) "Deep Metric Learning for Person Re-identification," in International Conference on Pattern Recognition. 34–39.

  45. Yu H-X, Zheng W-S, Wu A, Guo X, Gong S, Lai J-H (2019) Unsupervised Person Re-Identification by Soft Multilabel Learning. IEEE Conf Comput Vision Patt Recogn:2143–2152

  46. Zhang X, Luo H, Fan X, Xiang W, Sun Y, and Xiao Q (2017) "Alignedreid: Surpassing human-level performance in person re-identification," CoRR, abs/1711.08184

  47. Zhang X, Cao J, Shen C, and You M (2019) "Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification," in IEEE International Conference on Computer Vision , pp. 8221–8230.

  48. Zhang Y, Liu S, Qi L, Coleman S, Kerr D, Shi W (2020) Multi-level and multi-scale horizontal pooling network for person re-identification. Multimed Tools Appl 79:28603–28619

    Article  Google Scholar 

  49. Zheng L, Shen L, Tian L, Wang S, Wang J, and Tian Q (2015) "Scalable Person Re-identification: A Benchmark," in IEEE International Conference on Computer Vision, pp. 1116–1124.

  50. Zheng WS, Li X, Xiang T, Liao S, Lai J, and Gong S (2015) "Partial person re-identification," in IEEE International Conference on Computer Vision. pp. 4678–4686.

  51. Zheng Z, Zheng L, and Yang Y (2017) "Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro," in IEEE International Conference on Computer Vision, pp. 3774–3782.

  52. Zheng Z, Zheng L, Yang Y (2017) A discriminatively learned CNN embedding for person Reidentification. ACM Trans Multimed Comput Commun Appl 14:1–20

    Article  Google Scholar 

  53. Zhong Z, Zheng L, Cao D, and Li S (2017) "Re-ranking Person Re-identification with k-Reciprocal Encoding," in IEEE Conference on Computer Vision and Pattern Recogn, pp. 3652–3661.

  54. Z. Zhong, L. Zheng, S. Li, and Y. Yang, "Generalizing a person retrieval model hetero-and homogeneously," in Proceedings of the European Conference on Computer Vision, 2018, pp. 172–188.

  55. Zhong Z, Zheng L, Zheng Z, Li S, and Yang Y 2018 "Camera Style Adaptation for Person Re-identification," in IEEE Conference on Computer Vision and Pattern Recogn, pp. 5157–5166.

  56. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification. IEEE Conf Comput Vision Pattern Recogn:598–607

  57. Zhou B, Khosla A, Lapedriza A, Oliva A, and Torralba A (2016) "Learning Deep Features for Discriminative Localization," in IEEE Conference on Computer Vision and Pattern Recogn. 2921–2929.

  58. Zhu X, Zhu X, Li M, Murino V, Gong S (2019) Intra-Camera Supervised Person Re-Identification: A New Benchmark. IEEE Int Conf Comput Vision Workshop:1079–1087

Download references

Acknowledgments

This work is supported by the National Natural Science Foundation of China (No. 61872326, No. 61672475); Shandong Provincial Natural Science Foundation (ZR2019MF044).

Author information

Authors and Affiliations

  1. College of Information Science and Engineering, Ocean University of China, Qingdao, 266100, China

    Hui Zhu, Lei Huang, Zhiqiang Wei, Wenfeng Zhang & Huanhuan Cai

Authors
  1. Hui Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lei Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhiqiang Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wenfeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Huanhuan Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lei Huang.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhu, H., Huang, L., Wei, Z. et al. Learning camera invariant deep features for semi-supervised person re-identification. Multimed Tools Appl 81, 18671–18692 (2022). https://doi.org/10.1007/s11042-022-12581-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12581-0

Keywords

Search

Navigation