Table 6 Comparative experiments of different models on VOC_MASK dataset.
From: A small object detection model in aerial images based on CPDD-YOLOv8
Model | Precision (%) | Recall (%) | F1 (%) | mAP@0.5 (%) | mAP@0.5:0.95 (%) | Parameters (M) | FPS (f/s) | GFLOPs |
|---|---|---|---|---|---|---|---|---|
SSD | 94.7 | 52.0 | 67.1 | 84.3 | 55.2 | 24 | 7 | 24 |
Faster R-CNN | 57.7 | 80.7 | 67.2 | 86.4 | 53.0 | 250 | 32 | 250 |
YOLOv5 | 93.8 | 88.9 | 91.2 | 93.7 | 67.4 | 62 | 16 | 12 |
YOLOv7-tiny | 94.0 | 88.8 | 91.4 | 93.3 | 65.5 | 60 | 32 | 60 |
YOLOv8 | 94.1 | 88.1 | 91.0 | 93.2 | 67.6 | 111 | 52 | 111 |
YOLOv10 | 95.1 | 87.1 | 91.0 | 93.1 | 67.2 | 80.3 | 60 | 24.5 |
CPDD-YOLOv8 | 93.3 | 89.5 | 91.5 | 94.1 | 68.5 | 206 | 22 | 141.9 |
