An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions

TL;DR

This paper introduces an unsupervised domain adaptation framework for multimodal 2D object detection in adverse weather, combining data augmentation, cross-modal alignment, and pretext tasks to improve robustness across domains.

Contribution

It presents a novel unsupervised domain adaptation method that effectively adapts RGB and lidar-based 2D object detectors to adverse weather conditions, addressing heterogeneity in data distributions.

Findings

Significant performance improvement in adverse weather scenarios.

Effective domain gap reduction in both single-target and multi-target settings.

Enhanced robustness of multimodal object detection models.

Abstract

Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving. While deep learning architectures that fuse vision and range data for 2D object detection have thrived in recent years, the corresponding modalities can degrade in adverse weather or lighting conditions, ultimately leading to a drop in performance. Although domain adaptation methods attempt to bridge the domain gap between source and target domains, they do not readily extend to heterogeneous data distributions. In this work, we propose an unsupervised domain adaptation framework, which adapts a 2D object detector for RGB and lidar sensors to one or more target domains featuring adverse weather conditions. Our proposed approach consists of three components. First, a data augmentation scheme that simulates weather distortions is devised to add domain confusion and prevent overfitting on the source data. Second, to promote cross-domain foreground object alignment, we leverage the complementary features of multiple modalities through a multi-scale entropy-weighted domain discriminator. Finally, we use carefully designed pretext tasks to learn a more robust representation of the target domain data. Experiments performed on the DENSE dataset show that our method can substantially alleviate the domain gap under the single-target domain adaptation (STDA) setting and the less explored yet more general multi-target domain adaptation (MTDA) setting.