Fourier Domain Adaptation for Traffic Light Detection in Adverse Weather∗

Traffic light detection under adverse weather conditions remains largely unexplored in ADAS systems, with existing approaches relying on complex deep learning methods that introduce significant computational overheads during training and deployment. This paper proposes Fourier Domain Adaptation (FDA), which requires only training data modifications without architectural changes, enabling effective adaptation to rainy and foggy conditions. FDA minimizes the domain gap between source and target domain by manipulation of frequency components which allows to reduce the high frequency adverse weather effects of fog and rain, creating a dataset for reliable performance under adverse weather. Since low-frequency components encode global structural information while high-frequency components capture finer details, this transformation helps the model retain structural consistency while adapting to new environmental conditions. By training models with FDA-augmented data and labels of the source domain (target domain labels are absent), the model becomes more robust to domain shifts caused by adverse weather conditions. This method is especially helpful for mitigating the effects of rain or fog, as it can be challenging to find data with these conditions along with proper annotations. The source domain merged LISA and S²TLD datasets, processed to address class imbalance. Established methods simulated rainy and foggy scenarios to form the target domain. Semi-Supervised Learning (SSL) techniques were explored to leverage data more effectively, addressing the shortage of comprehensive datasets and poor performance of state-of-the-art models under hostile weather. Experimental results show FDA-augmented models outperform baseline models across mAP50, mAP50-95, Precision, and Recall metrics. YOLOv8 achieved a 12.25% average increase across all metrics. Average improvements of 7.69% in Precision, 19.91% in Recall, 15.85% in mAP50, and 23.81% in mAP50-95 were observed across all models, demonstrating FDA's effectiveness in mitigating adverse weather impact. These improvements enable real-world applications requiring reliable performance in challenging environmental conditions.