Table 1 Detection performances of the different models in the test dataset
From: Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields
| Model | Average inference time (ms) | mAP50 | C. sepium AP50 | Sugar beet AP50 |
|---|---|---|---|---|
| YOLO V3 | 40.75 | 0.832 | 0.726 | 0.938 |
| YOLO V3-tiny | 6.39 | 0.810 | 0.705 | 0.914 |
| Proposed | 6.48 | 0.829 | 0.761 | 0.897 |