Home > Research > Publications & Outputs > Hierarchical Connectivity-Centered Clustering f...

Links

Text available via DOI:

View graph of relations

Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification. / Bai, Yan; Wang, Ce; Lou, Yihang et al.
In: IEEE Transactions on Image Processing, Vol. 30, 31.12.2021, p. 6715-6729.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Bai, Y, Wang, C, Lou, Y, Liu, J & Duan, L-Y 2021, 'Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification', IEEE Transactions on Image Processing, vol. 30, pp. 6715-6729. https://doi.org/10.1109/TIP.2021.3094140

APA

Bai, Y., Wang, C., Lou, Y., Liu, J., & Duan, L.-Y. (2021). Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification. IEEE Transactions on Image Processing, 30, 6715-6729. https://doi.org/10.1109/TIP.2021.3094140

Vancouver

Bai Y, Wang C, Lou Y, Liu J, Duan LY. Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification. IEEE Transactions on Image Processing. 2021 Dec 31;30:6715-6729. Epub 2021 Jul 8. doi: 10.1109/TIP.2021.3094140

Author

Bai, Yan ; Wang, Ce ; Lou, Yihang et al. / Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification. In: IEEE Transactions on Image Processing. 2021 ; Vol. 30. pp. 6715-6729.

Bibtex

@article{96b111b6ceb64c378e3824f632c72e61,
title = "Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification",
abstract = "Unsupervised domain adaptation (UDA) on person Re-Identification (ReID) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain. Recent works mainly optimize the ReID models with pseudo labels generated by unsupervised clustering on the target domain. However, the pseudo labels generated by the unsupervised clustering methods are often unreliable, due to the severe intra-person variations and complicated cluster structures in the practical application scenarios. In this work, to handle the complicated cluster structures, we propose a novel learnable Hierarchical Connectivity-Centered (HCC) clustering scheme by Graph Convolutional Networks (GCNs) to generate more reliable pseudo labels. Our HCC scheme learns the complicated cluster structure by hierarchically estimating the connectivity among samples from the vertex level to cluster level in a graph representation, and thereby progressively refines the pseudo labels. Additionally, to handle the intra-person variations in clustering, we propose a novel relation feature for HCC clustering, which exploits the identities from the source domain as references to represent target domain samples. Experiments demonstrate that our method is able to achieve state-of-the art performance on three challenging benchmarks.",
author = "Yan Bai and Ce Wang and Yihang Lou and Jun Liu and Ling-Yu Duan",
year = "2021",
month = dec,
day = "31",
doi = "10.1109/TIP.2021.3094140",
language = "English",
volume = "30",
pages = "6715--6729",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identification

AU - Bai, Yan

AU - Wang, Ce

AU - Lou, Yihang

AU - Liu, Jun

AU - Duan, Ling-Yu

PY - 2021/12/31

Y1 - 2021/12/31

N2 - Unsupervised domain adaptation (UDA) on person Re-Identification (ReID) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain. Recent works mainly optimize the ReID models with pseudo labels generated by unsupervised clustering on the target domain. However, the pseudo labels generated by the unsupervised clustering methods are often unreliable, due to the severe intra-person variations and complicated cluster structures in the practical application scenarios. In this work, to handle the complicated cluster structures, we propose a novel learnable Hierarchical Connectivity-Centered (HCC) clustering scheme by Graph Convolutional Networks (GCNs) to generate more reliable pseudo labels. Our HCC scheme learns the complicated cluster structure by hierarchically estimating the connectivity among samples from the vertex level to cluster level in a graph representation, and thereby progressively refines the pseudo labels. Additionally, to handle the intra-person variations in clustering, we propose a novel relation feature for HCC clustering, which exploits the identities from the source domain as references to represent target domain samples. Experiments demonstrate that our method is able to achieve state-of-the art performance on three challenging benchmarks.

AB - Unsupervised domain adaptation (UDA) on person Re-Identification (ReID) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain. Recent works mainly optimize the ReID models with pseudo labels generated by unsupervised clustering on the target domain. However, the pseudo labels generated by the unsupervised clustering methods are often unreliable, due to the severe intra-person variations and complicated cluster structures in the practical application scenarios. In this work, to handle the complicated cluster structures, we propose a novel learnable Hierarchical Connectivity-Centered (HCC) clustering scheme by Graph Convolutional Networks (GCNs) to generate more reliable pseudo labels. Our HCC scheme learns the complicated cluster structure by hierarchically estimating the connectivity among samples from the vertex level to cluster level in a graph representation, and thereby progressively refines the pseudo labels. Additionally, to handle the intra-person variations in clustering, we propose a novel relation feature for HCC clustering, which exploits the identities from the source domain as references to represent target domain samples. Experiments demonstrate that our method is able to achieve state-of-the art performance on three challenging benchmarks.

U2 - 10.1109/TIP.2021.3094140

DO - 10.1109/TIP.2021.3094140

M3 - Journal article

VL - 30

SP - 6715

EP - 6729

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

ER -