aiqbench analysis
This research addresses a critical bottleneck in autonomous driving by proposing WA-ADDA, a domain adaptation technique that aligns non-street-view training data with real-world street-scene conditions under adverse weather. The study establishes a new benchmark and evaluation protocol to ensure models remain robust across diverse backbones like ResNet and EfficientNet while maintaining accuracy in clear weather. By specifically targeting the gap between synthetic or remote-source datasets and actual driving environments, this work advances the reliability of computer vision systems for safety-critical perception tasks.
Weather-Aware Domain Adaptation for Street-View Weather Recognition
arXiv:2610.02000v1 Announce Type: cross 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.
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.
7 pages, 3 figures, 4 tables. Published in the 2026 IEEE Conference on Technologies for Sustainability (SusTech)
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2610.02000 [cs.CV]
(or arXiv:2610.02000v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.02000 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1109/SUSTECH67720.2026.11536286 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 272 words
Related coverage
Advancing All-Weather Building Damage Mapping to the Instance Level: Outcomes and Insights from the 2026 Bright Challenge
arXiv · Jul 28, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors
arXiv · Aug 17, 2026