Table 2 Comparison of different methods on the WCYZ.
From: A semantic feature enhanced YOLOv5-based network for polyp detection from colonoscopy images
Methods | Precision | Recall | F-score | Time (s) |
---|---|---|---|---|
R-CNN | 0.907 | 0.889 | 0.897 | 1.180 |
Faster R-CNN | 0.914 | 0.896 | 0.905 | 0.375 |
YOLOv4 | 0.881 | 0.879 | 0.880 | 0.033 |
YOLOv7 | 0.783 | 0.764 | 0.773 | 0.024 |
YOLOv8 | 0.904 | 0.878 | 0.891 | 0.020 |
RT-DETR-R50 | 0.868 | 0.872 | 0.870 | 0.021 |
Ours | 0.916 | 0.923 | 0.919 | 0.034 |