Home

Awesome

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

Framework Fig

Created by Zeyu HU

Introduction

This work is based on our paper LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation, which appears at the European Conference on Computer Vision (ECCV) 2022.

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.

Citation

If you find our work useful in your research, please consider citing:

@inproceedings{hu2022lidal,
title={LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation},
author={Hu, Zeyu and Bai, Xuyang and Zhang, Runze and Wang, Xin and Sun, Guangyuan and Fu, Hongbo and Tai, Chiew-Lan},
booktitle={European Conference on Computer Vision},
pages={248--265},
year={2022},
organization={Springer}
}

Installation

Data Preparation

Run