Imitating targets from all sides: an unsupervised transfer learning method for person re-identification | International Journal of Machine Learning and Cybernetics Skip to main content
Springer Nature Link
Log in

Imitating targets from all sides: an unsupervised transfer learning method for person re-identification

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Person re-identification (Re-ID) models usually present a limited performance when they are trained on one dataset and tested on another dataset due to the inter-dataset bias (e.g. completely different identities and backgrounds) and the intra-dataset difference (e.g. camera and pose changes). In other words, the absence of identity labels (who the person is) and pairwise labels (whether a pair of images belongs to the same person or not) leads to failures in unsupervised person Re-ID problem. We argue that synchronous consideration of these two aspects can improve the performance of unsupervised person Re-ID model. In this work, we introduce a Classification and Latent Commonality (CLC) method based on transfer learning for the unsupervised person Re-ID problem. Our method has three characteristics: (1) proposing an imitate model to generate an imitated target domain with estimated identity labels and create a pseudo target domain to compensate the pairwise labels across camera views; (2) formulating a dual classification loss on both the source domain and imitated target domain to learn a discriminative representation and diminish the inter-domain bias; (3) investigating latent commonality and reducing the intra-domain difference by constraining triplet loss on the source domain, imitated target domain and pairwise label target domain (composed of pseudo target domain and target domain). Extensive experiments are conducted on three widely employed benchmarks, including Market-1501, DukeMTMC-reID and MSMT17, and experimental results demonstrate that the proposed method can achieve a competitive performance against other state-of-the-art unsupervised Re-ID approaches.

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
¥17,985 /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 includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3908–3916

  2. Bai S, Bai X (2016) Sparse contextual activation for efficient visual re-ranking. IEEE Trans Image Process 25(3):1056–1069

    Article  MathSciNet  Google Scholar 

  3. Baktashmotlagh M, Faraki M, Drummond T, Salzmann M (2018) Learning factorized representations for open-set domain adaptation. arXiv preprint arXiv:180512277

  4. Bazzani L, Cristani M, Murino V (2013) Symmetry-driven accumulation of local features for human characterization and re-identification. Comput Vis Image Underst 117(2):130–144

    Article  Google Scholar 

  5. Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1–2):151–175

    Article  MathSciNet  Google Scholar 

  6. Chang X, Yang Y, Xiang T, Hospedales TM (2018) Disjoint label space transfer learning with common factorised space. arXiv preprint arXiv:181202605

  7. Chen W, Chen X, Zhang J, Huang K (2017) Beyond triplet loss: a deep quadruplet network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 403–412

  8. Choi Y, Choi M, Kim M, Ha JW, Kim S, Choo J (2018) Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8789–8797

  9. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE, pp 248–255

  10. Deng W, Zheng L, Ye Q, Kang G, Yang Y, Jiao J (2018) Image–image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 994–1003

  11. Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification: clustering and fine-tuning. ACM Trans Multimed Comput (TOMM) 14(4):83

    Google Scholar 

  12. Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: 2010 IEEE Computer society conference on computer vision and pattern recognition, IEEE, pp 2360–2367

  13. Feng Y, Yuan Y, Lu X (2021) Person re-identification via unsupervised cross-view metric learning. In:  IEEE Transactions on Cybernetics, vol 51, pp 1849–1859. https://doi.org/10.1109/TCYB.2019.2909480

  14. Geng S, Yu M, Liu Y, Yu Y, Bai J (2019) Re-ranking pedestrian re-identification with multiple metrics. Multimed Tools Appl 78(9):11631–11653

    Article  Google Scholar 

  15. Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: European conference on computer vision, Springer, pp 262–275

  16. Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC (2017) Improved training of wasserstein gans. In Advances in neural information processing systems. Springer, New York, pp 5767–5777

    Google Scholar 

  17. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  18. He Z, Cheolkon J, Qingtao F, Zhendong Z (2018) Deep feature embedding learning for person re-identification based on lifted structured loss. Multimedia tools and applications. Springer, New York, pp 1–18

    Google Scholar 

  19. He Z, Zuo W, Kan M, Shan S, Chen X (2019) Attgan: Facial attribute editing by only changing what you want. IEEE Trans Image Process 28(11):5464–5478

    Article  MathSciNet  Google Scholar 

  20. Kalayeh MM, Basaran E, Gökmen M, Kamasak ME, Shah M (2018) Human semantic parsing for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1062–1071

  21. Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980

  22. Kodirov E, Xiang T, Gong S (2015) Dictionary learning with iterative Laplacian regularisation for unsupervised person re-identification. In: BMVC, vol 3, p 8

  23. Leng Q, Hu R, Liang C, Wang Y, Chen J (2015) Person re-identification with content and context re-ranking. Multimed Tools Appl 74(17):6989–7014

    Article  Google Scholar 

  24. Li W, Zhu X, Gong S (2018a) Harmonious attention network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285–2294

  25. Li YJ, Yang FE, Liu YC, Yeh YY, Du X, Frank Wang YC (2018b) Adaptation and re-identification network: an unsupervised deep transfer learning approach to person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 172–178

  26. Lian Q, Li W, Chen L, Duan L (2019) Known-class aware self-ensemble for open set domain adaptation. arXiv preprint arXiv:190501068

  27. Liao S, Hu Y, Zhu X, Li SZ (2015) Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2197–2206

  28. Lin S, Li H, Li CT, Kot AC (2018) Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. arXiv preprint arXiv:180701440

  29. Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. Proc AAAI Conf Artif Intell 2:1–8

    Google Scholar 

  30. Liu H, Cao Z, Long M, Wang J, Yang Q (2019) Separate to adapt: open set domain adaptation via progressive separation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2927–2936

  31. Liu X, Zhao H, Tian M, Sheng L, Shao J, Yi S, Yan J, Wang X (2017a) Hydraplus-net: attentive deep features for pedestrian analysis. In: Proceedings of the IEEE international conference on computer vision, pp 350–359

  32. Liu Z, Wang D, Lu H (2017b) Stepwise metric promotion for unsupervised video person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 2429–2438

  33. Long M, Cao Y, Wang J, Jordan MI (2015) Learning transferable features with deep adaptation networks. arXiv preprint arXiv:150202791

  34. Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International conference on machine learning, volume 70, JMLR. org, pp 2208–2217

  35. Ma B, Su Y, Jurie F (2014) Covariance descriptor based on bio-inspired features for person re-identification and face verification. Image Vis Comput 32(6–7):379–390

    Article  Google Scholar 

  36. Panareda Busto P, Gall J (2017) Open set domain adaptation. In: Proceedings of the IEEE international conference on computer vision, pp 754–763

  37. Peng P, Xiang T, Wang Y, Pontil M, Gong S, Huang T, Tian Y (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1306–1315

  38. Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision, Springer, pp 17–35

  39. Rohrbach M, Ebert S, Schiele B (2013) Transfer learning in a transductive setting. In Advances in neural information processing systems. Springer, New York, pp 46–54

    Google Scholar 

  40. Saito K, Yamamoto S, Ushiku Y, Harada T (2018) Open set domain adaptation by backpropagation. In: Proceedings of the European conference on computer vision (ECCV), pp 153–168

  41. Sener O, Song HO, Saxena A, Savarese S (2016) Learning transferrable representations for unsupervised domain adaptation. In Advances in neural information processing systems. Springer, New York, pp 2110–2118

    Google Scholar 

  42. Shu R, Bui HH, Narui H, Ermon S (2018) A dirt-t approach to unsupervised domain adaptation. arXiv preprint arXiv:180208735

  43. Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: The European conference on computer vision (ECCV)

  44. Tan S, Jiao J, Zheng WS (2019) Weakly supervised open-set domain adaptation by dual-domain collaboration. arXiv preprint arXiv:190413179

  45. Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:14123474

  46. Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7167–7176

  47. Wang F, Zuo W, Lin L, Zhang D, Zhang L (2016a) Joint learning of single-image and cross-image representations for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1288–1296

  48. Wang G, Lin L, Ding S, Li Y, Wang Q (2016b) Dari: distance metric and representation integration for person verification. In: Thirtieth AAAI conference on artificial intelligence

  49. Wang H, Gong S, Xiang T (2014a) Unsupervised learning of generative topic saliency for person re-identification. In: Proceedings of the British machine vision conference (BMVC)

  50. Wang J, Zhu X, Gong S, Li W (2018) Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2275–2284

  51. Wang Q, Gao J, Li X (2019a) Weakly supervised adversarial domain adaptation for semantic segmentation in urban scenes. IEEE Trans Image Process 28(9):4376–4386

    Article  MathSciNet  Google Scholar 

  52. Wang Q, Gao J, Lin W, Yuan Y (2019b) Learning from synthetic data for crowd counting in the wild. In: The IEEE conference on computer vision and pattern recognition (CVPR)

  53. Wang T, Gong S, Zhu X, Wang S (2014b) Person re-identification by video ranking. In: European conference on computer vision, Springer, pp 688–703

  54. Wei L, Zhang S, Gao W, Tian Q (2018a) Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 79–88

  55. Wei L, Zhang S, Yao H, Gao W, Tian Q (2018b) Glad: Global-local-alignment descriptor for scalable person re-identification. IEEE Trans Multimed 21(4):986–999

    Article  Google Scholar 

  56. Wu PW, Lin YJ, Chang CH, Chang EY, Liao SW (2019a) Relgan: Multi-domain image-to-image translation via relative attributes. In: Proceedings of the IEEE international conference on computer vision, pp 5914–5922

  57. Wu Y, Lin Y, Dong X, Yan Y, Ouyang W, Yang Y (2018) Exploit the unknown gradually: one-shot video-based person re-identification by stepwise learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5177–5186

  58. Wu Y, Lin Y, Dong X, Yan Y, Bian W, Yang Y (2019b) Progressive learning for person re-identification with one example. IEEE Trans Image Process 28(6):2872–2881

    Article  MathSciNet  Google Scholar 

  59. Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1249–1258

  60. Xu X, Li W, Xu D (2015) Distance metric learning using privileged information for face verification and person re-identification. IEEE Trans Neural Netw Learn Syst 26(12):3150–3162

    Article  MathSciNet  Google Scholar 

  61. Ye M, Liang C, Yu Y, Wang Z, Leng Q, Xiao C, Chen J, Hu R (2016) Person reidentification via ranking aggregation of similarity pulling and dissimilarity pushing. IEEE Trans Multimed 18(12):2553–2566

    Article  Google Scholar 

  62. Ye M, Ma AJ, Zheng L, Li J, Yuen PC (2017) Dynamic label graph matching for unsupervised video re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 5142–5150

  63. Yu HX, Wu A, Zheng WS (2017) Cross-view asymmetric metric learning for unsupervised person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 994–1002

  64. Yu HX, Zheng WS, Wu A, Guo X, Gong S, Lai JH (2019) Unsupervised person re-identification by soft multilabel learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2148–2157

  65. Yuan Y, Zhang J, Wang Q (2020) Deep Gabor convolution network for person re-identification. Neurocomputing 378:387–398

    Article  Google Scholar 

  66. Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 144–151

  67. Zhao R, Oyang W, Wang X (2017) Person re-identification by saliency learning. IEEE Trans Pattern Anal Mach Intell 39(2):356–370. https://doi.org/10.1109/TPAMI.2016.2544310

    Article  Google Scholar 

  68. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Proceedings of the IEEE international conference on computer vision, pp 1116–1124

  69. Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. arXiv preprint arXiv:161002984

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

  71. Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1318–1327

  72. Zhong Z, Zheng L, Li S, Yang Y (2018a) Generalizing a person retrieval model hetero-and homogeneously. In: Proceedings of the European conference on computer vision (ECCV), pp 172–188

  73. Zhong Z, Zheng L, Zheng Z, Li S, Yang Y (2018b) Camera style adaptation for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5157–5166

  74. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 598–607

  75. Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232

Download references

Acknowledgements

This work was supported the Natural Science Foundation of China (61972027) and the Beijing Municipal Natural Science Foundation (Grant no. 4212041).

Author information

Authors and Affiliations

  1. The School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China

    Jiajie Tian, Zhu Teng & Baopeng Zhang

  2. Baotou Railway Vocational and Technical College, Inner Mongolia, China

    Yanxue Wang

  3. AI Lab, Lenovo Research, Beijing, China

    Jianping Fan

Authors
  1. Jiajie Tian
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Zhu Teng
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Baopeng Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yanxue Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Jianping Fan
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Baopeng Zhang.

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

Tian, J., Teng, Z., Zhang, B. et al. Imitating targets from all sides: an unsupervised transfer learning method for person re-identification. Int. J. Mach. Learn. & Cyber. 12, 2281–2295 (2021). https://doi.org/10.1007/s13042-021-01308-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01308-6

Keywords