Data Shift of Object Detection in Autonomous Driving
It addresses performance degradation in autonomous driving systems due to data distribution changes like weather and seasonal variations, but the approach is incremental as it builds on existing methods.
This study tackled the data shift problem in autonomous driving object detection by analyzing its complexity and manifestations, and then constructing a model that integrates CycleGAN-based data augmentation with YOLOv5, achieving superior performance on the BDD100K dataset compared to baseline models.
With the widespread adoption of machine learning technologies in autonomous driving systems, their role in addressing complex environmental perception challenges has become increasingly crucial. However, existing machine learning models exhibit significant vulnerability, as their performance critically depends on the fundamental assumption that training and testing data satisfy the independent and identically distributed condition, which is difficult to guarantee in real-world applications. Dynamic variations in data distribution caused by seasonal changes, weather fluctuations lead to data shift problems in autonomous driving systems. This study investigates the data shift problem in autonomous driving object detection tasks, systematically analyzing its complexity and diverse manifestations. We conduct a comprehensive review of data shift detection methods and employ shift detection analysis techniques to perform dataset categorization and balancing. Building upon this foundation, we construct an object detection model. To validate our approach, we optimize the model by integrating CycleGAN-based data augmentation techniques with the YOLOv5 framework. Experimental results demonstrate that our method achieves superior performance compared to baseline models on the BDD100K dataset.