Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

• Published in: IEEE transactions on image processing Vol. 30; pp. 7815 - 7829
• Main Authors: Dai, Yongxing, Liu, Jun, Bai, Yan, Tong, Zekun, Duan, Ling-Yu
• Format: Journal Article
• Language: English
• Published: New York IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Algorithms; Cluster analysis; Clustering; Domains; Labels; Machine learning; Noise measurement; Person re-ID; Prototypes; pseudo label noise; Refining; Regularization; Reliability; Training; Training data; unsupervised domain adaption

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate pseudo labels, which can then be used as the supervision signa...