Learning deep embedding with mini-cluster loss for person re-identification

  • Caihong YuanEmail author
  • Jingjuan Guo
  • Ping Feng
  • Zhiqiang Zhao
  • Yihao Luo
  • Chunyan Xu
  • Tianjiang Wang
  • Kui DuanEmail author


Recently, the triplet loss is commonly used in many deep person re-identification (ReID) frameworks to learn an embedding space in which similar data points are close and dissimilar data points are far away. However, the triplet loss simply focuses on the relative orders of points. This may lead to a relatively large intra-class variance and then a weak generalization capacity on the test set. In this paper, we propose a mini-cluster loss, which regards images belonging to the same identity as a mini-cluster and treats them as a whole during the training instead of considering them separately. For each mini-cluster in a batch, we define the largest distance between points in a mini-cluster as its inner divergence and the shortest distance with outer points as its outer divergence. By constraining the outer divergence larger than the inner divergence, our framework with the mini-cluster loss achieves the more compact mini-clusters while keeping the diversity distributions of the classes. As a result, a better generalization ability and a higher performance can be obtained. In the extensive experiments, our proposed framework achieves a state-of-the-art performance on two large-scale person ReID datasets (Market1501, DukeMTMC-reID) which clearly demonstrates its effectiveness. Specifically, 72.44% mAP and 87.05% rank-1 score are achieved on the Market1501 dataset with single query setting, 78.17% mAP and 91.05% rank-1 score with multiply query setting, and on the DukeMTMC-reID dataset, 60.19% mAP and 77.20% rank-1 score are obtained.


Person re-identification Mini-cluster loss The triplet loss Deep feature embedding 



This work was supported by the National Natural Science Foundation of China (61572214, 61602244, U1536203 and U1504611), and partially sponsored by CCF-Tencent Open Research Fund.


  1. 1.
    Bai S, Bai X, Qi T (2017) Scalable person re-identification on supervised smoothed manifold. In: CVPR, pp 2530–2539Google Scholar
  2. 2.
    Barbosa IB, Cristani M, Caputo B, Rognhaugen A, Theoharis T (2017) Looking beyond appearances: synthetic training data for deep cnns in re-identification. Comput Vis Image Underst, 1–14Google Scholar
  3. 3.
    Chen Y, Chen Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. In: NIPS, pp 1988–1996Google Scholar
  4. 4.
    Chen W, Chen X, Zhang J, Huang K (2017) Beyond triplet loss: a deep quadruplet network for person re-identification. In: CVPR, pp 403–412Google Scholar
  5. 5.
    De C, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: CVPR, pp 1335–1344Google Scholar
  6. 6.
    Ding S, Lin L, Wang G, Chao H (2015) Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn 48(10):2993–3003CrossRefGoogle Scholar
  7. 7.
    Gong S, Cristani M, Yan S, Chen CL (2014) Person re-identification. SpringerGoogle Scholar
  8. 8.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778Google Scholar
  9. 9.
    Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv:1703.07737, 1–10
  10. 10.
    Huang Y, Xu J, Wu Q, Zheng Z, Zhang Z, Zhang J (2018) Multi-pseudo regularized label for generated samples in person re-identification. arXiv:1801.06742, 1–12
  11. 11.
    Li W, Wang X (2013) Locally aligned feature transforms across views. In: CVPR, pp 3594–3601Google Scholar
  12. 12.
    Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. In: ACCV, pp 31–44Google Scholar
  13. 13.
    Li Z, Chang S, Liang F, Huang TS, Cao L, Smith JR (2013) Learning locally-adaptive decision functions for person verification. In: CVPR, pp 3610–3617Google Scholar
  14. 14.
    Li D, Chen X, Zhang Z, Huang K (2017) Learning deep context-aware features over body and latent parts for person re-identification. In: CVPR, pp 384–393Google Scholar
  15. 15.
    Li W, Zhu X, Gong S (2017) Person re-identification by deep joint learning of multi-loss classification. IJCAI, 2194–2200Google Scholar
  16. 16.
    Liao S, Li SZ (2015) Efficient psd constrained asymmetric metric learning for person re-identification. In: ICCV, pp 3685–3693Google Scholar
  17. 17.
    Liu J, Zha ZJ, Qi T, Liu D, Yao T, Ling Q, Mei T (2016) Multi-scale triplet cnn for person re-identification. In: ACM on multimedia conference, pp 192–196Google Scholar
  18. 18.
    Matsukawa T, Okabe T, Suzuki E, Sato Y (2016) Hierarchical gaussian descriptor for person re-identification. In: CVPR, pp 1363–1372Google Scholar
  19. 19.
    Song HO, Yu X, Jegelka S, Savarese S (2016) Deep metric learning via lifted structured feature embedding. In: CVPR, pp 4004–4012Google Scholar
  20. 20.
    Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp 815–823Google Scholar
  21. 21.
    Shen Y, Lin W, Yan J, Xu M, Wu J, Wang J (2015) Person re-identification with correspondence structure learning. In: ICCV, pp 3200–3208Google Scholar
  22. 22.
    Shi H, Yang Y, Zhu X, Liao S, Lei Z, Zheng W, Li SZ (2016) Embedding deep metric for person re-identification: a study against large variations. In: ECCV, pp 732–748Google Scholar
  23. 23.
    Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. In: NIPS, pp 1857–1865Google Scholar
  24. 24.
    Su C, Yang F, Zhang S, Qi T, Davis LS, Gao W (2015) Multi-task learning with low rank attribute embedding for person re-identification. In: CVPR, pp 3739–3747Google Scholar
  25. 25.
    Sun Y, Zheng L, Deng W, Wang S (2017) Svdnet for pedestrian retrieval. ICCV, 3800–3808Google Scholar
  26. 26.
    Van Der Maaten L (2014) Accelerating t-sne using tree-based algorithms, vol 15Google Scholar
  27. 27.
    Vezzani R, Baltieri D, Cucchiara R (2013) People reidentification in surveillance and forensics:a survey. Acm Comput Surv 46(2):1–37CrossRefGoogle Scholar
  28. 28.
    Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E (2018) Deep learning for computer vision: a brief review. In: Comput Intell Neurosci, pp 1–13Google Scholar
  29. 29.
    Wang F, Zuo W, Lin L, Zhang D, Zhang L (2016) Joint learning of single-image and cross-image representations for person re-identification. In: CVPR, pp 1288–1296Google Scholar
  30. 30.
    Wang J, Zhou F, Wen S, Liu X, Lin Y (2017) Deep metric learning with angular loss. In: ICCV, pp 2593–2601Google Scholar
  31. 31.
    Wen Y, Zhang K, Li Z, Yu Q (2016) A discriminative feature learning approach for deep face recognition. In: ECCV, pp 499–515Google Scholar
  32. 32.
    Wu S, Chen YC, Li X, Wu AC, You JJ, Zheng WS (2016) An enhanced deep feature representation for person re-identification. In: WACV, pp 1–8Google Scholar
  33. 33.
    Wu C-Y, Manmatha R, Smola AJ, Krahenbuhl P (2017) Sampling matters in deep embedding learning. In: CVPR, pp 2840–2848Google Scholar
  34. 34.
    Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: CVPR, pp 1249–1258Google Scholar
  35. 35.
    Xiao T, Li S, Wang B, Lin L, Wang X (2017) Joint detection and identification feature learning for person search. In: CVPR, pp 3376–3385Google Scholar
  36. 36.
    Xu J, Zhao R, Zhu F, Wang H, Ouyang W (2018) Attention-aware compositional network for person re-identification. CVPR, 2119–2128Google Scholar
  37. 37.
    Yang Y, Lei Z, Zhang S, Shi H, Li SZ (2016) Metric embedded discriminative vocabulary learning for high-level person representation. In: AAAI, pp 3648–3654Google Scholar
  38. 38.
    Yang Y, Wen L, Lyu S, Li SZ (2017) Unsupervised learning of multi-level descriptors for person re-identification. In: AAAI, vol 1, pp 4306–4312Google Scholar
  39. 39.
    Yi D, Lei Z, Li SZ (2014) Deep metric learning for practical person re-identification. Comput Sci, 34–39Google Scholar
  40. 40.
    Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification. In: CVPR, pp 1239–1248Google Scholar
  41. 41.
    Zhang X, Fang Z, Wen Y, Li Z, Yu Q (2017) Range loss for deep face recognition with long-tail. ICCV, 1–10Google Scholar
  42. 42.
    Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In: CVPR, pp 144–151Google Scholar
  43. 43.
    Zheng WS, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPR, pp 649–656Google Scholar
  44. 44.
    Zheng W, Gong S, Xiang T (2013) Reidentification by relative distance comparison. IEEE Trans Pattern Anal Mach Intell 35(3):653–668CrossRefGoogle Scholar
  45. 45.
    Zheng L, Shen L, Lu T, Wang S, Wang J, Qi T (2015) Scalable person re-identification: a benchmark. In: ICCV, pp 1116–1124Google Scholar
  46. 46.
    Zheng Z, Zheng L, Yang Y (2017) A discriminatively learned cnn embedding for person re-identification. arXiv:1611.05666, 1–10
  47. 47.
    Zheng Z, Zheng L, Yi Y (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro. ICCV, 3754–3762Google Scholar
  48. 48.
    Zhou S, Wang J, Wang J, Gong Y, Zheng N (2017) Point to set similarity based deep feature learning for person reidentification. In: CVPR, pp 3741–3750Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Caihong Yuan
    • 1
    • 2
    Email author
  • Jingjuan Guo
    • 1
    • 3
  • Ping Feng
    • 1
  • Zhiqiang Zhao
    • 3
  • Yihao Luo
    • 1
  • Chunyan Xu
    • 4
  • Tianjiang Wang
    • 1
  • Kui Duan
    • 5
    Email author
  1. 1.School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhanChina
  2. 2.School of Computer and Information EngineeringHenan UniversityKaifengChina
  3. 3.School of Information Science and TechnologyJiujiang UniversityJiujiangChina
  4. 4.School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjingChina
  5. 5.Huazhong University of Science and TechnologyWuhanChina

Personalised recommendations