Two-Stage Clustering Pseudo-Labels Correction for Cross-Domain Person Re-Identification

Two-Stage Clustering Pseudo-Labels Correction for Cross-Domain Person Re-Identification

The same identity of person images captured by multiple cameras may encounter appearance change significantly. In this case, most cluster-based cross-domain person re-identification(re-id) methods easily group them into different groups, which may generate lots of noise pseudo labels and limit the m...

Full description

Bibliographic Details
Main Authors: Fei Zhou, Chaoxi Zhang, Yang Lin, Tao Li
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Person re-identification
unsupervised domain adaptation
pseudo-labels correction
Online Access:https://ieeexplore.ieee.org/document/9458281/

Internet

https://ieeexplore.ieee.org/document/9458281/

Similar Items