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

• Published in: IEEE transactions on image processing Vol. 30; pp. 6715 - 6729
• Main Authors: Bai, Yan, Wang, Ce, Lou, Yihang, Liu, Jun, Duan, Ling-Yu
• Format: Journal Article
• Language: English
• Published: New York IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Clustering; Clustering methods; Connectivity; Data mining; Domains; Feature extraction; graph convolutional networks; Graph representations; Graph theory; Graphical representations; Knowledge management; Labels; person re-identification; Training; Training data; Unsupervised domain adaptation; Visualization
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2021.3094140

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.