1. LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
- Author
-
Hu, Zeyu, Bai, Xuyang, Zhang, Runze, Wang, Xin, Sun, Guangyuan, Fu, Hongbo, and Tai, Chiew-Lan
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
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., Comment: ECCV 2022, supplementary materials included
- Published
- 2022