arXiv：cs.LG（机器学习，全量分类）· Hossein Maghsoumi, George Atia, Yaser P. Fallah·· 15 小时前AI 评分34
WA-ADDA：面向街景天气识别的天气感知域自适应方法
Weather-Aware Domain Adaptation for Street-View Weather Recognition
AI 导读
研究者提出天气感知对抗判别域自适应方法 WA-ADDA，通过让域判别器以预测天气为条件，学习兼具域不变性与天气敏感性的特征。该方法整合多个非街景天气数据集为源域、真实街景图像为目标域，构建多数据集基准并以宏平均准确率为主要指标。
正文
Abstract:Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather recognition from street-view images under domain shift, where most available training data come from non-street-view sources that differ markedly from real driving scenes. We propose Weather-Aware Adversarial Discriminative Domain Adaptation (WA-ADDA), which conditions the domain discriminator on predicted weather to promote features that are both domain-invariant and weather-sensitive. We also assemble a multi-dataset benchmark by unifying diverse non-street-view weather collections as sources and real street-view images as targets, and define a standardized evaluation protocol with macro accuracy as the primary metric. Across backbones (ResNet-50, EfficientNet, VGG, DenseNet), WA-ADDA consistently improves street-view performance and yields strong per-class recalls in challenging conditions while preserving clear-weather accuracy. These findings highlight the feasibility of domain-adapted weather recognition and the value of our benchmark for advancing robust, on-board perception.
| Comments: | 7 pages, 3 figures, 4 tables. Published in the 2026 IEEE Conference on Technologies for Sustainability (SusTech) |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02000 [cs.CV] |
| (or arXiv:2610.02000v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02000 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | 2026 IEEE Conference on Technologies for Sustainability (SusTech), 2026 |
| Related DOI: | https://doi.org/10.1109/SUSTECH67720.2026.11536286
DOI(s) linking to related resources |
Submission history
From: Hossein Maghsoumi [view email]
[v1]
Thu, 1 Oct 2026 16:31:43 UTC (1,520 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org