发表机构
University of Central Florida（中佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对自动驾驶街景天气识别中的域偏移问题，提出天气感知对抗性判别域适应（WA-ADDA），统一多数据集基准，显著提升多种骨干网络在不利天气下的识别性能。
AI 中文摘要
雨、雪、雾和沙尘等不利条件对自动驾驶中基于摄像头的感知仍然具有挑战性。我们研究在域偏移下从街景图像进行多类天气识别，其中大多数可用的训练数据来自非街景来源，这些来源与真实驾驶场景显著不同。我们提出了天气感知对抗性判别域适应（WA-ADDA），该方法将域判别器条件化于预测的天气上，以促进既具有域不变性又具有天气敏感性的特征。我们还通过将多样化的非街景天气数据集统一为源域，并将真实街景图像作为目标域，构建了一个多数据集基准，并定义了一个标准化的评估协议，以宏平均准确率作为主要指标。在多种骨干网络（ResNet-50、EfficientNet、VGG、DenseNet）上，WA-ADDA持续提高了街景性能，并在具有挑战性的条件下产生了强大的每类召回率，同时保持了晴朗天气的准确率。这些发现凸显了域适应天气识别的可行性，以及我们的基准对于推进鲁棒的板载感知的价值。
英文摘要
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.
Comments7 pages, 3 figures, 4 tables. Published in the 2026 IEEE Conference on Technologies for Sustainability (SusTech)
Journal ref2026 IEEE Conference on Technologies for Sustainability (SusTech), 2026
DOI：10.1109/SUSTECH67720.2026.11536286
