Shedding Light on Darkness: Enhancing Object Detection Robustness with Synthetic Perturbations for Real-world Challenges

Abstract

Robustness against distribution shifts is crucial for object detection models in real-world applications. In this study, we evaluate the performance of four state-of-the-art models against natural perturbations, retrain them with synthetic perturbations using the AugLy augmentation package, and assess their improved performance against natural perturbations. Our empirical ablation study focuses on the brightness perturbation modality using the COCO 2017 and ExDARK datasets. Our findings suggest that synthetic perturbations can effectively improve model robustness against real-world distribution shifts, providing valuable insights for deploying robust object detection models in real-world scenarios.