Abstract
Recently developed clustering-guided unsupervised methods have shown their superior performance in the person re-identification (re-ID) problem, which aims to match the surveillance images containing the same person. However, the performance of these methods is usually very sensitive to the change of the hyper-parameters in the clustering methods, such as the maximum distance of the neighbors and the number of clusters, which determine the quality of the clustering results. Tuning these parameters may need a large-scale labeled validation set, which is usually not applicable in unlabeled domain and hard to be generalized to different datasets. To solve this problem, we propose a Loose-Tight Alternate Clustering method without using any sensitive clustering parameter for unsupervised optimization. Specifically, we address the challenge as a multi-domain clustering problem, and propose the Loose and Tight Bounds to alleviate two kinds of clustering errors. Based on these bounds, a novel Loose-Tight alternate clustering strategy is adopted to optimize the visual model iteratively. Furthermore, a quality measurement based learning method is proposed to mitigate the side-effects of the pseudo-label noise by assigning lower weight to those clusters with lower purity. Extensive experiments show that our method can not only outperform state-of-the-art methods without manual exploration of clustering parameters, but also achieve much higher robustness against the dynamic changing of the target domain.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)
Ester, M., Kriegel, H., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD (1996)
Fan, H., Zheng, L., Yan, C., Yang, Y.: Unsupervised person re-identification: clustering and fine-tuning. ACM (TOMM) (2018)
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: ICCV (2019)
Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: ICLR (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: NeurIPS (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Jung, A.B., et al.: Imgaug (2020). https://github.com/aleju/imgaug. Accessed 01 Feb 2020
Liang, Z., Liyue, S., Lu, T., Shengjin, W., Jingdong, W., Qi, T.: Scalable person re-identification: a benchmark. In: ICCV (2015)
Lin, Y., Dong, X., Zheng, L., Yan, Y., Yang, Y.: A bottom-up clustering approach to unsupervised person re-identification. In: AAAI (2019)
Lin, Y., Xie, L., Wu, Y., Yan, C., Tian, Q.: Unsupervised person re-identification via softened similarity learning. In: CVPR (2020)
Luo, C., Song, C., Zhang, Z.: Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In: ECCV (2020)
Mekhazni, D., Bhuiyan, A., Ekladious, G.S.E., Granger, E.: Unsupervised domain adaptation in the dissimilarity space for person re-identification. In: ECCV (2020)
Song, L., et al.: Unsupervised domain adaptive re-identification: theory and practice. Pattern Recogn. (2020)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV (2018)
Wang, D., Zhang, S.: Unsupervised person re-identification via multi-label classification. In: CVPR (2020)
Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: ACM MM (2018)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)
Wu, A., Zheng, W., Lai, J.: Unsupervised person re-identification by camera-aware similarity consistency learning. In: ICCV (2019)
Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR (2017)
Xuan, S., Zhang, S.: Intra-inter camera similarity for unsupervised person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11926–11935 (2021)
Yang, Q., Yu, H., Wu, A., Zheng, W.: Patch-based discriminative feature learning for unsupervised person re-identification. In: CVPR (2019)
Zeng, K., Ning, M., Wang, Y., Guo, Y.: Hierarchical clustering with hard-batch triplet loss for person re-identification. In: CVPR (2020)
Zhai, Y., et al.: Ad-cluster: augmented discriminative clustering for domain adaptive person re-identification. In: CVPR (2020)
Zhang, X., Cao, J., Shen, C., You, M.: Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: ICCV (2019)
Zheng, F., et al.: Pyramidal person re-identification via multi-loss dynamic training. In: CVPR (2019)
Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR (2017)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI (2020)
Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero-and homogeneously. In: ECCV (2018)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: CVPR (2019)
Zhun, Z., Liang, Z., Zhiming, L., Shaozi, L., Yi, Y.: Learning to adapt invariance in memory for person re-identification. In: TPAMI (2020)
Zou, Y., Yang, X., Yu, Z., Kumar, B.V.K.V., Kautz, J.: Joint disentangling and adaptation for cross-domain person re-identification. In: ECCV (2020)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61876065), the Special Fund Project of Marine Economy Development in Guangdong Province([2021]35), and Guangzhou Science and Technology Program key projects (202007040002).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, B., Liang, T., Lv, J., Chen, S., Xie, H. (2022). Unsupervised Person Re-ID via Loose-Tight Alternate Clustering. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13369. Springer, Cham. https://doi.org/10.1007/978-3-031-10986-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-10986-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10985-0
Online ISBN: 978-3-031-10986-7
eBook Packages: Computer ScienceComputer Science (R0)