Dual-Level Viewpoint-Learning for Cross-Domain Vehicle Re-Identification

The definition of vehicle viewpoint annotations is ambiguous due to human subjective judgment, which makes the cross-domain vehicle re-identification methods unable to learn the viewpoint invariance features during source domain pre-training. This will further lead to cross-view misalignment in down...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Electronics (Basel) 2024-05, Vol.13 (10), p.1823
Hauptverfasser:	Zhou, Ruihua, Wang, Qi, Cao, Lei, Xu, Jianqiang, Zhu, Xiaogang, Xiong, Xin, Zhang, Huiqi, Zhong, Yuling
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Algorithms Annotations Bias Cameras Identification methods Invariance Learning Misalignment Orientation Teaching methods Unmanned aerial vehicles Vehicles
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!