Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
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 -