Abstract
Unsupervised person re-identification (re-ID) aims to identify the same person in unsupervised settings, which is a realistic and challenging problem due to getting rid of the dependence on annotations. Existing pseudo-label-based methods have been proved to be effective by discriminative representation learning and high-quality pseudo labels. However, there are some undesirable similarity structures in images affected by different states (e.g., backgrounds, occlusions, or other target confusions) which may generate noisy labels and lead to model degradation. To tackle the above issues, this paper analyzes the key factors for unsupervised re-ID performance from two perspectives: network structure and loss function. Specifically, we propose a multi-confidence contrastive learning with feature refinement (MCFR) model which can enhance the feature discriminative ability and meanwhile alleviate the impact of noisy data. For network architecture, a feature refined block is embedded into a multi-branch network, constructing FR-net. For loss function, a multi-confidence contrastive loss (MCCL) based on similarity and confidence relationship is developed. MCCL can flexibly update the list of hard negative samples in clusters and outliers, promoting the model by learning from confident samples. Extensive experiments including visualizations and ablation studies validate the effectiveness of each component in the MCFR model. Additionally, compared with the state-of-the-art unsupervised re-ID methods, our method achieves considerable performance on three benchmark datasets.
Similar content being viewed by others
Data availability
Dataset derived from public resources and made available with the article. The datasets analyzed during the current study are available in the [repository name Market1501] [10.1109/ICCV.2015.133] reference number [43], [repository name DukeMTMC-reID] reference number [44] and [repository name MSMT17] [10.1145/3394171.3413904] reference number [45].
References
Lin, X., Ren, P., Yeh, C.H., Yao, L., Song, A., Chang, X.: Unsupervised person re-identification: a systematic survey of challenges and solutions. arXiv:2109.06057 (2021)
Ge, Y., Chen, D. Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv:2001.01526 (2020)
Chen, H., Lagadec, B., Bremond, F.: Enhancing diversity in teacher-student networks via asymmetric branches for unsupervised person re-identification. arXiv:2011.13776 (2020)
Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. ACM Trans. Multimed. Comput. Commun. Appl. 14(4), 1–18 (2018)
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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2020)
Yang, F., Li, Ke., Zhong, Z., Luo, Z.: Asymmetric co-teaching for unsupervised crossdomain person re-identification. Proc. AAAI Conf. Artificial Intell. 34(07), 12597–12604 (2020)
Li, J., Zhang, S.: Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In: 2020 Proceedings of the IEEE International Conference on Computer Vision (ECCV), (2020)
Chen, Y., Zhu, X., Shaogang: Instance-guided context rendering for cross-domain person re-identification. In: The IEEE International Conference on Learning Representations (ICCV), pp. 232–242 (2019)
Lin, S., Li, H., Li, C.T., Kot, A.C.: Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. In BMVC, (2018)
Chang, W.-G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7354–7362 (2019)
Lin, Y., Dong, X., Zheng, L., Yan, Y., Yang, Yi.: A bottom-up clustering approach to unsupervised person re-identification. Proc. AAAI Conf. Artif. Intell. 33, 8738–8745 (2019)
Zeng, K., Ning, M., Wang, Y., Guo, Y.: Hierarchical clustering with hard-batch triplet loss for person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13657–13665 (2020)
Wang, D., Zhang, S.: Unsupervised person re-identification via multi-label classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10981–10990.444 (2020)
Hao, C., Wang, Y., Lagadec, B., Dantcheva, A., Francois, B.: Joint generative and contrastive learning for unsupervised person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021)
Lin, Y., Xie, L., Wu, Y., Yan, C., Tian, Q.: Unsupervised person re-identification via softened similarity learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3387–3396 (2020)
Ge, Y., Zhu, F., Chen, D., Zhao, R., Li, H.: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: Advances in Neural Information Processing Systems, (2020)
Li, M., Li, C.-G., Guo, J.: Cluster-guided asymmetric contrastive learning for unsupervised person reidentification, in arXiv:2106.07846, (2021)
Lin, Y., Xie, L., Wu, Y., Yan, C., Tian, Q.: Unsupervised person re-identification via softened similarity learning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3390–3399 (2020)
Ji, Z., Zou, X., Lin, X., Liu, X., Huang, T., Wu, S.: An attention-driven two-stage clustering method for unsupervised person re-identification. In: Proceedings of the European Conference on Computer Vision (ECCV), (2020)
Zhang, X., Ge, Y., Qiao, Q., Li, H.: Refining pseudo labels with clustering consensus over generations for unsupervised object re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021)
Chen, H., Lagadec, B., Bremond, F.: Ice: inter-instance contrastive encoding for unsupervised person re-identification. In: The IEEE International Conference on Computer Vision (ICCV) (2021)
Hong, Q.Y., Yu, H., Wu, A., Zheng, W.: Patch-based discriminative feature learning for unsupervised person reidentification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3633–3642 (2019)
Wang, D., Zhang, S.: Unsupervised person re-identification via multi-label classification. Int. J. Comput. Vis. 130, 2924–2939 (2022)
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) 2016, pp. 770–778 (2016)
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. In: Advances in neural information processing systems, (2018)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on machine learning, pp.1597–1607 (2020)
Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 1–14 (2020)
Guo, Y., Xu, M., Li, J. Ni, B., Zhu, X., Sun, Z., Xu, Y.: HCSC: hierarchical contrastive selective coding. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)
Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018).
Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European Conference on Computer Vision (ECCV), (2018)
Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: The IEEE International Conference on Computer Vision (ICCV) (2019)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: 34th Conference on Neural Information Processing Systems (NeurIPS), (2020)
Li, Y., Hu, P., Liu, Z., Peng, D., Zhou, J. T., Peng, X.: Contrastive clustering. In: Conference on Artificial Intelligence (AAAI) (2021)
Wang, X., Liu, Z., Yu, S.X.: Unsupervised feature learning by cross-level instance-group discrimination. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Junnan, L., Zhou, P., Xiong, C., Hoi, S.C.H.: Prototypical contrastive learning of unsupervised representations. In: International Conference on Learning Representations (ICLR) (2021)
Yang, F., Zhong, Z. Luo, Z., Cai, Y., Lin, Y., Li, S., Sebe, N.: Joint noise-tolerant learning and meta camera shift adaptation for un-supervised person re-identification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. Pp. 4855–4864 (2021)
Gutmann, M., Hyvarinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, pp. 297–304 (2010)
Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlu, D.: Hard negative mixing for contrastive learning, in arXiv: 2010.01028 (2020).
Robinson, J., Chuang, C., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: International Conference on Learning Representations (ICLR) (2021)
Wang, X., et al., Cross-batch memory for embedding learning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (2020)
Zhang, X., Mei, C.L., Chen, D.G., Li, J.H.: Multi-confidence rule acquisition and confidence-preserved attribute reduction in interval-valued decision systems Internat. J. Approx. Reason. 55(8), 1787–1804 (2014)
Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021)
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), (2015)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), (2016).
Liu, X., Zhang, S., Domain adaptive person re-identification via coupling optimization. In: Proceedings of the 28th ACM International Conference on Multimedia, pp.547–555 (2020).
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., FeiFei, L, Imagenet: a large-scale hierarchical image database. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248–255 (2009)
Han, X., Yu, X., Li, G., Zhao, J., Pan, G., Ye, Q., Jiao, J., Han, Z.: Rethinking sampling strategies for unsupervised person re-identification. arXiv: 2107.03024 (2021)
Cheng, D., Zhou, J., Wang, N., Gao, X.: hybrid dynamic contrast and probability distillation for unsupervised person Re-Id. IEEE Trans. Image Process. 31, 3334 (2022)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 62172029 and No. 61872030).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No potential conflict of interest was reported by the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Peng, W., Chen, H., Li, Y. et al. MCFR: multi-confidence contrastive learning with feature refined for unsupervised person re-identification. Vis Comput 40, 1853–1866 (2024). https://doi.org/10.1007/s00371-023-02890-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-023-02890-2