Tri-Invariance Contrastive Framework for Robust Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) has been proven very effective and it boosts the performance in learning representations from unlabeled data in the dataset. Most current methods have good accuracy, but there are two main problems. First, clustering often generates noisy labels. Second,...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Lei Wang, Chengang Liu, Xiaoxiao Wang, Weidong Gao, Xuejian Ge, Shunjie Zhu
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2025-11-01
Schriftenreihe:	Mathematics
Schlagworte:	person reidentification contrastive learning unsupervised learning robust modeling
Online-Zugang:	https://www.mdpi.com/2227-7390/13/21/3570
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!