LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

November 11, 2022 · Entered Twilight · 🏛 European Conference on Computer Vision

Repo contents: Processing_files, README.md, Semantic_kitti, check_points, dataset, docs, evaluate.py, network, nuScenes, pcl_related, score, train.py, utils

Authors Zeyu Hu, Xuyang Bai, Runze Zhang, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai arXiv ID 2211.05997 Category cs.CV: Computer Vision Citations 23 Venue European Conference on Computer Vision Repository https://github.com/hzykent/LiDAL ⭐ 34 Last Checked 1 month ago

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.