Weather-Aware Domain Adaptation for Street-View Weather Recognition

2026-10-01

AI Summary

This study addresses the challenge of adverse weather recognition in autonomous driving caused by distribution shifts between non-street-view training data and real-world scenarios. To this end, it proposes WA-ADDA, a novel adversarial discriminative domain adaptation framework that uniquely conditions on predicted weather. By integrating backbone networks such as ResNet and EfficientNet for feature alignment, the method effectively balances domain invariance with weather sensitivity. Furthermore, a multi-dataset benchmark and standardized evaluation protocol are established. Experimental results demonstrate that WA-ADDA significantly improves street-view weather recognition accuracy across various backbones, exhibiting particularly strong recall performance under severe conditions including rain, snow, fog, and dust.

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.

Problem

• weather recognition
• domain adaptation
• street-view images
• autonomous driving
• domain shift

Innovation

• Domain Adaptation
• Weather Recognition
• Adversarial Learning
• Autonomous Driving
• Benchmark