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.
@article{arxiv.2211.05997,
title = {LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation},
author = {Zeyu Hu and Xuyang Bai and Runze Zhang and Xin Wang and Guangyuan Sun and Hongbo Fu and Chiew-Lan Tai},
journal= {arXiv preprint arXiv:2211.05997},
year = {2022}
}