ATF-3D: Semi-Supervised 3D Object Detection With Adaptive Thresholds Filtering Based on Confidence and Distance

Performance of current point cloud-based outdoor 3D object detection relies heavily on large-scale high-quality 3D annotations. However, such annotations are usually expensive to collect and outdoor scenes easily accumulate massive unlabeled data containing rich scenes. Semi-supervised learning is a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE robotics and automation letters 2022-10, Vol.7 (4), p.10573-10580
Hauptverfasser:	Zhang, Zehan, Ji, Yang, Cui, Wei, Wang, Yulong, Li, Hao, Zhao, Xian, Li, Duo, Tang, Sanli, Yang, Ming, Tan, Wenming, Pu, Shiliang
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Adaptive search techniques Annotations autonomous agents Iterative methods localization Object detection Object recognition Performance enhancement Point cloud compression segmentation and categorization Semi-supervised learning Solid modeling Three dimensional models Three-dimensional displays Thresholds Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!