Table 4 Comparison of precision and recall between clean and noisy subsets for all models.

From: Robustness analysis of YOLO and faster R-CNN for object detection in realistic weather scenarios with noise augmentation

Model

Precision (clean)

Recall (clean)

Precision (noisy)

Recall (noisy)

YOLOv5s

0.78

0.47

0.71

0.42

YOLOv8m

0.79

0.73

0.74

0.65

YOLOv10n

0.76

0.68

0.69

0.62

Faster R-CNN

0.81

0.72

0.78

0.70

Back to article page