LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
This addresses the high annotation burden in 3D perception for autonomous driving, offering a significant reduction in labeling effort while maintaining performance.
The paper tackles the problem of reducing annotation costs for 3D LiDAR semantic segmentation by proposing LiDAL, an active learning method that uses inter-frame uncertainty to select samples, achieving 95% of fully supervised performance with less than 5% of annotations on SemanticKITTI and nuScenes datasets.
We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by exploiting inter-frame uncertainty among LiDAR frames. Our core idea is that a well-trained model should generate robust results irrespective of viewpoints for scene scanning and thus the inconsistencies in model predictions across frames provide a very reliable measure of uncertainty for active sample selection. To implement this uncertainty measure, we introduce new inter-frame divergence and entropy formulations, which serve as the metrics for active selection. Moreover, we demonstrate additional performance gains by predicting and incorporating pseudo-labels, which are also selected using the proposed inter-frame uncertainty measure. Experimental results validate the effectiveness of LiDAL: we achieve 95% of the performance of fully supervised learning with less than 5% of annotations on the SemanticKITTI and nuScenes datasets, outperforming state-of-the-art active learning methods. Code release: https://github.com/hzykent/LiDAL.