Inconsistency-based Active Learning for LiDAR Object Detection
This work addresses the costly data labeling issue for autonomous driving systems, but it is incremental as it extends existing active learning methods from images to LiDAR.
The paper tackled the problem of reducing labeling costs for LiDAR object detection in autonomous driving by proposing inconsistency-based active learning strategies, achieving the same mAP as random sampling with 50% of the labeled data.
Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for training. Acquiring and labeling such data is costly, necessitating the development of new strategies to optimize this process. Active learning is a promising approach that has been extensively researched in the image domain. In our work, we extend this concept to the LiDAR domain by developing several inconsistency-based sample selection strategies and evaluate their effectiveness in various settings. Our results show that using a naive inconsistency approach based on the number of detected boxes, we achieve the same mAP as the random sampling strategy with 50% of the labeled data.