The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration

Active learning strategies for 3D object detection in autonomous driving datasets may help to address challenges of data imbalance, redundancy, and high-dimensional data. We demonstrate the effectiveness of entropy querying to select informative samples, aiming to reduce annotation costs and improve...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-01
Hauptverfasser:	Greer, Ross, Bjørk Antoniussen, Andersen, Mathias V, Møgelmose, Andreas, Trivedi, Mohan M
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Datasets Empirical analysis Entropy Learning Object recognition Random sampling Redundancy Three dimensional models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!