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

Abstract--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 model performance. We experiment using the BEVFusion model for 3D object detection on the nuScenes dataset, comparing active learning to random sampling and demonstrating that entropy querying outperforms in most cases. Many autonomous driving tasks rely on supervised learning, and task performance under such methods is heavily dependent on accurate, high-volume data annotation. The conventional A. Redundancy and Data Imbalance approach for most autonomous driving tasks, such as 3D object As a motivating example, consider a fleet which seeks to detection [1, 2, 3, 4, 5], is to ask humans to label (or supervise gather data in a particular region. By the nature of our roadway the labeling of) all data collected in driving, then train learning system, over time, vehicles will likely encounter the same roads machines using the labeled data.