Enhancing Vehicle Detection under Adverse Weather Conditions with Contrastive Learning
This addresses the problem of domain shifts and visibility challenges in remote sensing for vehicle detection in Nordic regions, but it is incremental as it builds on existing methods like YOLO and contrastive learning.
The paper tackled vehicle detection in UAV images under adverse Nordic weather conditions like snow, using a sideload-CL-adaptation framework that leverages unannotated data to improve performance, resulting in a 3.8% to 9.5% increase in mAP50 on the NVD dataset.
Aside from common challenges in remote sensing like small, sparse targets and computation cost limitations, detecting vehicles from UAV images in the Nordic regions faces strong visibility challenges and domain shifts caused by diverse levels of snow coverage. Although annotated data are expensive, unannotated data is cheaper to obtain by simply flying the drones. In this work, we proposed a sideload-CL-adaptation framework that enables the use of unannotated data to improve vehicle detection using lightweight models. Specifically, we propose to train a CNN-based representation extractor through contrastive learning on the unannotated data in the pretraining stage, and then sideload it to a frozen YOLO11n backbone in the fine-tuning stage. To find a robust sideload-CL-adaptation, we conducted extensive experiments to compare various fusion methods and granularity. Our proposed sideload-CL-adaptation model improves the detection performance by 3.8% to 9.5% in terms of mAP50 on the NVD dataset.