V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Baolu, Li, Jinlong, Liu, Xinyu, Xu, Runsheng, Tu, Zhengzhong, Guo, Jiacheng, Li, Xiaopeng, Yu, Hongkai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912283457748992
author Li, Baolu
Li, Jinlong
Liu, Xinyu
Xu, Runsheng
Tu, Zhengzhong
Guo, Jiacheng
Li, Xiaopeng
Yu, Hongkai
author_facet Li, Baolu
Li, Jinlong
Liu, Xinyu
Xu, Runsheng
Tu, Zhengzhong
Guo, Jiacheng
Li, Xiaopeng
Yu, Hongkai
contents Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the domain gap. In this paper, we propose a Domain Generalization based approach, named \textit{V2X-DGW}, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Our research aims to not only maintain favorable multi-agent performance in the clean weather but also promote the performance in the unseen adverse weather conditions by learning only on the clean weather data. To realize the Domain Generalization, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weather-invariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). To evaluate this research, we add Fog, Rain, Snow conditions on two publicized multi-agent datasets based on physics-based models, resulting in two new datasets: OPV2V-w and V2XSet-w. Extensive experiments demonstrate that our V2X-DGW achieved significant improvements in the unseen adverse weathers. The code is available at https://github.com/Baolu1998/V2X-DGW.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions
Li, Baolu
Li, Jinlong
Liu, Xinyu
Xu, Runsheng
Tu, Zhengzhong
Guo, Jiacheng
Li, Xiaopeng
Yu, Hongkai
Computer Vision and Pattern Recognition
Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the domain gap. In this paper, we propose a Domain Generalization based approach, named \textit{V2X-DGW}, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Our research aims to not only maintain favorable multi-agent performance in the clean weather but also promote the performance in the unseen adverse weather conditions by learning only on the clean weather data. To realize the Domain Generalization, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weather-invariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). To evaluate this research, we add Fog, Rain, Snow conditions on two publicized multi-agent datasets based on physics-based models, resulting in two new datasets: OPV2V-w and V2XSet-w. Extensive experiments demonstrate that our V2X-DGW achieved significant improvements in the unseen adverse weathers. The code is available at https://github.com/Baolu1998/V2X-DGW.
title V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.11371