Abstract
Unsupervised person re-identification (Re-ID) is more substantial than the supervised one because it does not require any labeled samples. Currently, the most advanced unsupervised Re-ID models generate pseudo-labels to group images into different clusters and then establish a memory bank to calculate contrastive loss between instances and clusters. This framework has been proven to be remarkably efficient for unsupervised person Re-ID tasks. However, clustering operation inevitably produces misclassification, which brings noises and difficulties to contrastive learning and affects the initialization and updating of the prototype features stored in the memory bank. To solve this problem, we propose a new robust unsupervised person Re-ID model with two developed modules: Cluster Sample Aggregation module (CSA) and Hard Positive Sampling strategy (HPS). The CSA module aggregates each sample in the same cluster through the multi-head self-attention mechanism. This process enables the initialization of prototypes based on the similarities observed within clusters. Additionally, the HPS strategy extracts the dispersion degree of each sample by means of a self-attention aggregation module (SAA) that has been trained by CSA module. According to the obtained indicators, the hardest positive sample is sampled to update the prototype feature stored in the memory bank. With the self-attention mechanism fusing the information among instances in each cluster, the implicit relationships between samples can be better explored in a more refined way. Experiments show that our method achieves state-of-the-art results against existing unsupervised baselines on Market-1501, PersonX, and MSMT17 datasets.
Similar content being viewed by others
Data availability
The dataset used in this paper is publicly accessible based on cited references. In addition, the data that support the findings of this study are available on request from the first author, [Huibin Lin], upon reasonable request.
References
Zhai Y, Ye Q, Lu S, Jia M, Ji R, Tian Y (2020) Multiple expert brainstorming for domain adaptive person re-identification. In: Proceedings of the European Conference on computer vision, pp 594–611
Song X, Jin Z (2022) Domain adaptive attention-based dropout for one-shot person re-identification. Int J Mach Learn Cybern 13:255–268
Ge Y, Zhu F, Chen D, Zhao R, et al (2020) Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: Advances in neural information processing systems, vol. 33, pp 11309–11321
Yao H, Xu C (2021) Dual cluster contrastive learning for object re-identification. arXiv preprint arXiv:2112.04662
Hu Z, Zhu C, He G (2021) Hard-sample guided hybrid contrast learning for unsupervised person re-identification. In: 2021 7th IEEE International Conference on network intelligence and digital content, pp 91–95
Chen H, Lagadec B, Bremond F (2021) Ice: inter-instance contrastive encoding for unsupervised person re-identification. In: Proceedings of the IEEE International Conference on computer vision, pp 14960–14969
Ester M, Kriegel H-P, Sander J, Xu X, et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Kdd, vol. 96, pp. 226–231
Xie K, Wu Y, Xiao J, Li J, Xiao G, Cao Y (2021) Unsupervised person re-identification via k-reciprocal encoding and style transfer. Int J Mach Learn Cybern 12:2899–2916
Bachman P, Hjelm RD, Buchwalter W (2019) Learning representations by maximizing mutual information across views. In: Advances in neural information processing systems, vol. 32
Tian Y, Krishnan D, Isola P (2020) Contrastive multiview coding. In: Proceedings of the European Conference on computer vision, pp 776–794
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
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
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 33, pp 8738–8745
Dai Z, Wang G, Zhu S, Yuan W, Tan P (2021) Cluster contrast for unsupervised person re-identification. arXiv preprint arXiv:2103.11568
Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv e-prints, 1807
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 815–823
Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 10981–10990
Ren Z, Zhang Y, Wang S (2022) Lcdae: data augmented ensemble framework for lung cancer classification. Technol Cancer Res Treat 21:1–14
Xiao T, Li S, Wang B, Lin L, Wang X (2017) Joint detection and identification feature learning for person search. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3415–3424
He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 9729–9738
Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International Conference on machine learning, pp 1597–1607
Zhang X, Ge Y, Qiao Y, Li H (2021) Refining pseudo labels with clustering consensus over generations for unsupervised object re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3436–3445
Zhou H, Kong J, Jiang M, Liu T (2023) Heterogeneous dual network with feature consistency for domain adaptation person re-identification. Int J Mach Learn Cybern 14(5):1951–1965
Liu Y, Ge H, Sun L, Hou Y (2022) Complementary attention-driven contrastive learning with hard-sample exploring for unsupervised domain adaptive person re-id. IEEE Trans Circuits Syst Video Technol 33(1):326–341
Ren Z, Wang S, Zhang Y (2023) Weakly supervised machine learning. CAAI Trans Intell Technol 8:1–32
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30
Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H (2021) Training data-efficient image transformers & distillation through attention. In: International Conference on machine learning, pp 10347–10357
Zhang Y, Deng L, Zhu H, Wang W, Ren Z, Zhou Q, Lu S, Sun S, Zhu Z, Gorriz JM et al (2023) Deep learning in food category recognition. Inform Fusion, p 101859
Cai D, Lam W (2020) Graph transformer for graph-to-sequence learning. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 34, pp 7464–7471
Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. In: Advances in neural information processing systems, vol. 32
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 248–255. Ieee
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
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
Wei L, Zhang S, Gao W, Tian Q (2018) 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
Sun X, Zheng L (2019) Dissecting person re-identification from the viewpoint of viewpoint. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 608–617
Riccitiello J (2015) John riccitiello sets out to identify the engine of growth for unity technologies (interview). VentureBeat. Interview with Dean Takahashi. Retrieved January 18(3)
Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proc. IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), vol. 3, pp. 1–7
Lin Y, Xie L, Wu Y, Yan C, Tian Q (2020) Unsupervised person re-identification via softened similarity learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3390–3399
Li J, Zhang S (2020) Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In: Proceedings of the European Conference on computer vision, pp 483–499
Chen H, Wang Y, Lagadec B, Dantcheva A, Bremond F (2021) Joint generative and contrastive learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2004–2013
Wang M, Lai B, Huang J, Gong X, Hua X-S (2021) Camera-aware proxies for unsupervised person re-identification. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 2, p 4
Li M, Li C-G, Guo J (2022) Cluster-guided asymmetric contrastive learning for unsupervised person re-identification. IEEE Trans Image Process 31:3606–3617
Radenović F, Tolias G, Chum O (2018) Fine-tuning cnn image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 41(7):1655–1668
Rosvall M, Bergstrom CT (2008) Maps of random walks on complex networks reveal community structure. Proc Natl Acad Sci 105(4):1118–1123
Ge Y, Chen D, Li H (2020) Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv preprint arXiv:2001.01526
Li M, Zhu X, Gong S (2018) Unsupervised person re-identification by deep learning tracklet association. In: Proceedings of the European Conference on computer vision, pp 737–753
Wu J, Yang Y, Liu H, Liao S, Lei Z, Li SZ (2019) Unsupervised graph association for person re-identification. In: Proceedings of the IEEE International Conference on computer vision, pp 8321–8330
Wang Z, Zhang J, Zheng L, Liu Y, Sun Y, Li Y, Wang S (2020) Cycas: self-supervised cycle association for learning re-identifiable descriptions. In: Proceedings of the European Conference on computer vision, pp 72–88
Acknowledgements
This research is sponsored in part by the National Natural Science Foundation of China under Grant no. 62076065 and the Natural Science Foundation of Fujian Province under Grant no. 2020J01495.
Author information
Authors and Affiliations
Corresponding 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
Lin, H., Fu, HT., Zhang, CY. et al. A new robust contrastive learning for unsupervised person re-identification. Int. J. Mach. Learn. & Cyber. 15, 1779–1793 (2024). https://doi.org/10.1007/s13042-023-01997-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01997-1