Domain Generalization in Autonomous Driving: Evaluating YOLOv8s, RT-DETR, and YOLO-NAS with the ROAD-Almaty Dataset
This research addresses domain generalization challenges for autonomous driving systems in underrepresented regions like Kazakhstan, but it is incremental as it applies existing models to a new dataset without novel methodological contributions.
This study evaluated the domain generalization of three object detection models (YOLOv8s, RT-DETR, YOLO-NAS) on the ROAD-Almaty dataset in Kazakhstan, finding that RT-DETR outperformed others with an average F1-score of 0.672 at IoU=0.5, but all models showed significant performance drops under challenging conditions like heavy snowfall.
This study investigates the domain generalization capabilities of three state-of-the-art object detection models - YOLOv8s, RT-DETR, and YOLO-NAS - within the unique driving environment of Kazakhstan. Utilizing the newly constructed ROAD-Almaty dataset, which encompasses diverse weather, lighting, and traffic conditions, we evaluated the models' performance without any retraining. Quantitative analysis revealed that RT-DETR achieved an average F1-score of 0.672 at IoU=0.5, outperforming YOLOv8s (0.458) and YOLO-NAS (0.526) by approximately 46% and 27%, respectively. Additionally, all models exhibited significant performance declines at higher IoU thresholds (e.g., a drop of approximately 20% when increasing IoU from 0.5 to 0.75) and under challenging environmental conditions, such as heavy snowfall and low-light scenarios. These findings underscore the necessity for geographically diverse training datasets and the implementation of specialized domain adaptation techniques to enhance the reliability of autonomous vehicle detection systems globally. This research contributes to the understanding of domain generalization challenges in autonomous driving, particularly in underrepresented regions.