Enhancing object detection robustness: A synthetic and natural perturbation approach. (arXiv:2304.10622v1 [cs.CV])

Robustness against real-world distribution shifts is crucial for the
successful deployment of object detection models in practical applications. In
this paper, we address the problem of assessing and enhancing the robustness of
object detection models against natural perturbations, such as varying lighting
conditions, blur, and brightness. We analyze four state-of-the-art deep neural
network models, Detr-ResNet-101, Detr-ResNet-50, YOLOv4, and YOLOv4-tiny, using
the COCO 2017 dataset and ExDark dataset. By simulating synthetic perturbations
with the AugLy package, we systematically explore the optimal …

analyze applications art arxiv dataset deep neural network deployment detection distribution lighting natural network neural network package paper practical resnet resnet-50 robustness state synthetic world