Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification

no code implementations • CVPR 2020 • Kaiwei Zeng

Base on these, we explore how to make use of the similarity of samples to conduct a fully unsupervised method which just trains on the unlabeled target dataset.

Clustering Unsupervised Domain Adaptation +1

Energy Clustering for Unsupervised Person Re-identification

no code implementations • 31 Aug 2019 • Kaiwei Zeng

Due to the high cost of data annotation in supervised learning for person re-identification (Re-ID) methods, unsupervised learning becomes more attractive in the real world.

Clustering Transfer Learning +1