Table 6 Performance comparison Of PEYOLO And YOLOv10 families.
From: PEYOLO a perception efficient network for multiscale surface defects detection
Methods | Params↓ | GFLOPS↓ | FPS↑ | \({\text{mAP}}_{50}\)↑ | F1 scores↑ | P↑ | R↑ |
|---|---|---|---|---|---|---|---|
YOLOv10n | 2.77 | 8.7 | 136.2 | 69.4 | 0.64 | 0.634 | 0.639 |
YOLOv10s | 8.12 | 25.1 | 139.8 | 70.3 | 0.68 | 0.67 | 0.683 |
YOLOv10m | 16.57 | 64.5 | 74.7 | 74.5 | 0.7 | 0.743 | 0.671 |
YOLOv10l | 25.88 | 127.9 | 44.5 | 72.8 | 0.67 | 0.704 | 0.648 |
PEYOLO | 3.09 | 7.5 | 125.4 | 78.1 | 0.72 | 0.709 | 0.745 |
