Generalizing a Person Retrieval Model Hetero- and Homogeneously

  • Zhun Zhong
  • Liang Zheng
  • Shaozi Li
  • Yi Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11217)


Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras. Given a labeled source training set and an unlabeled target training set, we aim to improve the generalization ability of re-ID models on the target testing set. To this end, we introduce a Hetero-Homogeneous Learning (HHL) method. Our method enforces two properties simultaneously: (1) camera invariance, learned via positive pairs formed by unlabeled target images and their camera style transferred counterparts; (2) domain connectedness, by regarding source/target images as negative matching pairs to the target/source images. The first property is implemented by homogeneous learning because training pairs are collected from the same domain. The second property is achieved by heterogeneous learning because we sample training pairs from both the source and target domains. On Market-1501, DukeMTMC-reID and CUHK03, we show that the two properties contribute indispensably and that very competitive re-ID UDA accuracy is achieved. Code is available at:


Person re-identification Unsupervised domain adaptation 



This work is supported by the National Nature Science Foundation of China (No. 61572409, No. U1705286 & No. 61571188), Fujian Province 2011Collaborative Innovation Center of TCM Health Management, Collaborative Innovation Center of Chinese Oolong Tea Industry-Collaborative Innovation Center (2011) of Fujian Province, Fund for Integration of Cloud Computing and Big Data, Innovation of Science and Education, the Data to Decisions CRC (D2D CRC) and the Cooperative Research Centres Programme. Zhun Zhong thanks Wenjing Li for encouragement.


  1. 1.
    Bazzani, L., Cristani, M., Murino, V.: Symmetry-driven accumulation of local features for human characterization and re-identification. CVIU (2013)Google Scholar
  2. 2.
    Ben-David, S., et al.: A theory of learning from different domains. Mach. Learn. 79, 151–175 (2010)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR (2017)Google Scholar
  4. 4.
    Chen, M., Weinberger, K.Q., Blitzer, J.: Co-training for domain adaptation. In: Advances in Neural Information Processing Systems, pp. 2456–2464 (2011)Google Scholar
  5. 5.
    Choi, Y., et al.: Stargan: unified generative adversarial networks for multi-domain image-to-image translation. In: CVPR (2018)Google Scholar
  6. 6.
    Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  7. 7.
    Deng, W., et al.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR (2018)Google Scholar
  8. 8.
    Dong, X., Yan, Y., Ouyang, W., Yang, Y.: Style aggregated network for facial landmark detection. In: CVPR (2018)Google Scholar
  9. 9.
    Dong, X., et al.: Supervision-by-Registration: an unsupervised approach to improve the precision of facial landmark detectors. In: CVPR (2018)Google Scholar
  10. 10.
    Fan, H., Zheng, L., Yang, Y.: Unsupervised person re-identification: Clustering and fine-tuning. arXiv preprint arXiv:1705.10444 (2017)
  11. 11.
    Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR (2016)Google Scholar
  12. 12.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  13. 13.
    Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008). Scholar
  14. 14.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  15. 15.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
  16. 16.
    Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. arXiv preprint arXiv:1711.03213 (2017)
  17. 17.
    Hu, J., Lu, J., Tan, Y.P.: Deep transfer metric learning. In: CVPR (2015)Google Scholar
  18. 18.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)Google Scholar
  19. 19.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)Google Scholar
  20. 20.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  21. 21.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  22. 22.
    Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: CVPR (2014)Google Scholar
  23. 23.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: CVPR (2015)Google Scholar
  24. 24.
    Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. In: NIPS (2016)Google Scholar
  25. 25.
    Liu, Z., Wang, D., Lu, H.: Stepwise metric promotion for unsupervised video person re-identification. In: ICCV (2017)Google Scholar
  26. 26.
    Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  27. 27.
    Luo, Y., Zheng, Z., Zheng, L., Guan, T., Yu, J., Yang, Y.: Macro-micro adversarial network for human parsing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part IX. LNCS, vol. 11217, pp. 424–440. Springer, Cham (2018)CrossRefGoogle Scholar
  28. 28.
    Peng, P., et al.: Unsupervised cross-dataset transfer learning for person re-identification. In: CVPR (2016)Google Scholar
  29. 29.
    Qin, D., Gammeter, S., Bossard, L., Quack, T., Van Gool, L.: Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors. In: CVPR (2011)Google Scholar
  30. 30.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: ECCVW (2016)Google Scholar
  31. 31.
    Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: NIPS (2013)Google Scholar
  32. 32.
    Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. arXiv preprint arXiv:1702.08400 (2017)
  33. 33.
    Sener, O., Song, H.O., Saxena, A., Savarese, S.: Learning transferrable representations for unsupervised domain adaptation. In: NIPS (2016)Google Scholar
  34. 34.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR (2014)Google Scholar
  35. 35.
    Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI (2016)Google Scholar
  36. 36.
    Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). Scholar
  37. 37.
    Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)
  38. 38.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR (2018)Google Scholar
  39. 39.
    Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)Google Scholar
  40. 40.
    Wu, Y., et al.: Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In: CVPR (2018)Google Scholar
  41. 41.
    Yan, H., et al.: Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation. In: CVPR (2017)Google Scholar
  42. 42.
    Yu, H., Wu, A., Zheng, W.S.: Cross-view asymmetric metric learning for unsupervised person re-identification. In: ICCV (2017)Google Scholar
  43. 43.
    Zheng, L., et al.: Scalable person re-identification: a benchmark. In: ICCV (2015)Google Scholar
  44. 44.
    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016)
  45. 45.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: ICCV (2017)Google Scholar
  46. 46.
    Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR (2017)Google Scholar
  47. 47.
    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. arXiv preprint arXiv:1708.04896 (2017)
  48. 48.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: CVPR (2018)Google Scholar
  49. 49.
    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
  50. 50.
    Zhu, X.: Semi-supervised learning literature survey. Technical report, University of Wisconsin-Madison (2005)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Cognitive Science DepartmentXiamen UniversityXiamenChina
  2. 2.Centre for Artificial IntelligenceUniversity of Technology SydneyUltimoAustralia
  3. 3.Research School of Computer ScienceAustralian National UniversityCanberraAustralia

Personalised recommendations