Table 6 Comparison experiments of different models on the TinyPerson dataset.(CF-YOLO is an enhanced version based on YOLOv11n).
From: CF-YOLO for small target detection in drone imagery based on YOLOv11 algorithm
Model | P | R | F1 | mAP50 | mAP50:95 | Para(M) | GFLOPs |
|---|---|---|---|---|---|---|---|
YOLOv5n | 38.7 | 21.5 | 27.8 | 19.3 | 6.18 | 2.18 | 5.8 |
YOLOv5s | 42 | 23.2 | 29.9 | 22.4 | 7.4 | 7.81 | 18.7 |
YOLOv8n | 38.6 | 21.8 | 27.9 | 20 | 6.51 | 2.68 | 6.8 |
YOLOv8s | 41.3 | 23.2 | 29.7 | 22.3 | 7.44 | 9.82 | 23.3 |
YOLOv9-tiny | 38.5 | 20.5 | 26.6 | 19 | 6.01 | 1.73 | 6.4 |
YOLOv9s | 41.3 | 22.5 | 29.0 | 21.3 | 6.92 | 6.19 | 22.1 |
YOLOv10n | 38.4 | 21.9 | 27.9 | 19.3 | 6.19 | 2.26 | 6.5 |
YOLOv10s | 40.3 | 23.7 | 29.9 | 22.4 | 7.48 | 7.21 | 21.4 |
YOLOv11n | 38.4 | 22.3 | 28.3 | 19.6 | 6.21 | 2.58 | 6.3 |
YOLOv11s | 40.3 | 23.2 | 29.5 | 21.7 | 7.15 | 9.41 | 21.3 |
CF-YOLO | 46.8 | 31.8 | 38.0 | 29.7 | 9.81 | 3.77 | 23.9 |
