Advertisement

Multiple Expert Brainstorming for Domain Adaptive Person Re-Identification

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12352)

Abstract

Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored. In this paper, we propose a multiple expert brainstorming network (MEB-Net) for domain adaptive person re-ID, opening up a promising direction about model ensemble problem under unsupervised conditions. MEB-Net adopts a mutual learning strategy, where multiple networks with different architectures are pre-trained within a source domain as expert models equipped with specific features and knowledge, while the adaptation is then accomplished through brainstorming (mutual learning) among expert models. MEB-Net accommodates the heterogeneity of experts learned with different architectures and enhances discrimination capability of the adapted re-ID model, by introducing a regularization scheme about authority of experts. Extensive experiments on large-scale datasets (Market-1501 and DukeMTMC-reID) demonstrate the superior performance of MEB-Net over the state-of-the-arts. Code is available at https://github.com/YunpengZhai/MEB-Net.

Keywords

Domain adaptation Person re-ID Ensemble learning 

Notes

Acknowledgement

This work is partially supported by grants from the National Key R&D Program of China under grant 2017YFB1002400, the National Natural Science Foundation of China (NSFC) under contract No. 61825101, U1611461 and 61836012.

References

  1. 1.
    Anil, R., Pereyra, G., Passos, A., Ormandi, R., Dahl, G.E., Hinton, G.E.: Large scale distributed neural network training through online distillation. arXiv preprint arXiv:1804.03235 (2018)
  2. 2.
    Bagherinezhad, H., Horton, M., Rastegari, M., Farhadi, A.: Label refinery: improving ImageNet classification through label progression. arXiv preprint arXiv:1805.02641 (2018)
  3. 3.
    Chen, T., Goodfellow, I., Shlens, J.: Net2Net: accelerating learning via knowledge transfer. arXiv preprint arXiv:1511.05641 (2015)
  4. 4.
    Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: IEEE CVPR (2009)Google Scholar
  5. 5.
    Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: IEEE CVPR (2018)Google Scholar
  6. 6.
    Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. TOMCCAP 14(4), 83:1–83:18 (2018)Google Scholar
  7. 7.
    Fan, H., Zheng, L., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. CoRR abs/1705.10444 (2017)Google Scholar
  8. 8.
    Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 6112–6121 (2019)Google Scholar
  9. 9.
    Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv preprint arXiv:2001.01526 (2020)
  10. 10.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016Google Scholar
  11. 11.
    Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
  12. 12.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708 (2017)Google Scholar
  13. 13.
    Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646–661. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_39CrossRefGoogle Scholar
  14. 14.
    Jia, M., Zhai, Y., Lu, S., Ma, S., Zhang, J.: A similarity inference metric for RGB-infrared cross-modality person re-identification. In: IJCAI 2020, June 2020Google Scholar
  15. 15.
    Jin, X., Lan, C., Zeng, W., Chen, Z.: Global distance-distributions separation for unsupervised person re-identification. arXiv preprint arXiv:2006.00752 (2020)
  16. 16.
    Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3143–3152 (2020)Google Scholar
  17. 17.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  18. 18.
    Li, Y.J., Lin, C.S., Lin, Y.B., Wang, Y.C.F.: Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 7919–7929 (2019)Google Scholar
  19. 19.
    Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.J.: Learning from noisy labels with distillation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1910–1918 (2017)Google Scholar
  20. 20.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
  21. 21.
    Lin, S., Li, H., Li, C., Kot, A.C.: Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. In: BMVC (2018)Google Scholar
  22. 22.
    Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: IEEE CVPR (2019)Google Scholar
  23. 23.
    Liu, Z., Wang, D., Lu, H.: Stepwise metric promotion for unsupervised video person re-identification. In: IEEE ICCV, pp. 2448–2457 (2017)Google Scholar
  24. 24.
    Lv, J., Wang, X.: Cross-dataset person re-identification using similarity preserved generative adversarial networks. In: Liu, W., Giunchiglia, F., Yang, B. (eds.) KSEM, pp. 171–183 (2018)Google Scholar
  25. 25.
    Peng, P., et al.: Unsupervised cross-dataset transfer learning for person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016Google Scholar
  26. 26.
    Qi, L., Wang, L., Huo, J., Zhou, L., Shi, Y., Gao, Y.: A novel unsupervised camera-aware domain adaptation framework for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 8080–8089 (2019)Google Scholar
  27. 27.
    Ristani, E., Solera, F., Zou, R.S., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: IEEE ECCV Workshops (2016)Google Scholar
  28. 28.
    Shen, Z., He, Z., Xue, X.: Meal: Multi-model ensemble via adversarial learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4886–4893 (2019)Google Scholar
  29. 29.
    Singh, S., Hoiem, D., Forsyth, D.: Swapout: Learning an ensemble of deep architectures. In: Advances in Neural Information Processing Systems, pp. 28–36 (2016)Google Scholar
  30. 30.
    Song, L., et al.: Unsupervised domain adaptive re-identification: Theory and practice. CoRR abs/1807.11334 (2018)Google Scholar
  31. 31.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  32. 32.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826 (2016)Google Scholar
  33. 33.
    Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, pp. 1195–1204 (2017)Google Scholar
  34. 34.
    Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066 (2013)Google Scholar
  35. 35.
    Wang, J., Zhu, X., Gong, S., Li, W.: Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: IEEE CVPR (2018)Google Scholar
  36. 36.
    Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: IEEE CVPR (2018)Google Scholar
  37. 37.
    Wu, J., Liao, S., Lei, Z., Wang, X., Yang, Y., Li, S.Z.: Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification. In: IEEE ICME, pp. 886–891 (2019)Google Scholar
  38. 38.
    Wu, Y., Lin, Y., Dong, X., Yan, Y., Ouyang, W., Yang, Y.: Exploit the unknown gradually: one-shot video-based person re-identification by stepwise learning. In: IEEE CVPR (2018)Google Scholar
  39. 39.
    Yang, F., et al.: Part-aware progressive unsupervised domain adaptation for person re-identification. IEEE Trans. Multimed. (2020)Google Scholar
  40. 40.
    Yang, F., Yan, K., Lu, S., Jia, H., Xie, X., Gao, W.: Attention driven person re-identification. Pattern Recogn. 86, 143–155 (2019)CrossRefGoogle Scholar
  41. 41.
    Ye, M., Ma, A.J., Zheng, L., Li, J., Yuen, P.C.: Dynamic label graph matching for unsupervised video re-identification. In: IEEE ICCV, pp. 5152–5160 (2017)Google Scholar
  42. 42.
    Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4133–4141 (2017)Google Scholar
  43. 43.
    Zhai, Y., Lu, S., Ye, Q., Shan, X., Chen, J., Ji, R., Tian, Y.: Ad-cluster: augmented discriminative clustering for domain adaptive person re-identification. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020Google Scholar
  44. 44.
    Zhang, X., Cao, J., Shen, C., You, M.: Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 8222–8231 (2019)Google Scholar
  45. 45.
    Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4320–4328 (2018)Google Scholar
  46. 46.
    Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868–884. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_52CrossRefGoogle Scholar
  47. 47.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: The IEEE International Conference on Computer Vision (ICCV), December 2015Google Scholar
  48. 48.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: IEEE ICCV (2017)Google Scholar
  49. 49.
    Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero- and homogeneously. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 176–192. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01261-8_11CrossRefGoogle Scholar
  50. 50.
    Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: IEEE CVPR (2019)Google Scholar
  51. 51.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: CamStyle: a novel data augmentation method for person re-identification. IEEE TIP 28(3), 1176–1190 (2019)MathSciNetGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Electronic and Computer EngineeringPeking UniversityBeijingChina
  2. 2.Department of Computer Science and TechnologyPeking UniversityBeijingChina
  3. 3.University of Chinese Academy of SciencesBeijingChina
  4. 4.Nanyang Technological UniversitySingaporeSingapore
  5. 5.Xiamen UniversityXiamenChina

Personalised recommendations