Table 4 Model performance effect using YOLOv5n and adding C3CA, C3ECA, C3CBAM, C3SE respectively. Significant values are in bold.
From: An improved YOLOv5n algorithm for detecting surface defects in industrial components
Method | AP (%) | mAP@50 (%) | Params (M) | |||||
|---|---|---|---|---|---|---|---|---|
CR | IN | PA | PS | RS | SC | |||
YOLOv5n | 35.8 | 85.8 | 80.8 | 85.5 | 51.6 | 86.4 | 71 | 1.76 |
YOLOv5n + C3CA | 37.3 | 87.9 | 80.3 | 83.3 | 56.8 | 89.9 | 72.5 | 1.86 |
YOLOv5n + C3ECA | 40.2 | 87.4 | 81.1 | 86.3 | 55.2 | 87.4 | 72.2 | 1.76 |
YOLOv5n + C3CBAM | 39.6 | 87.8 | 77.4 | 87.8 | 45.8 | 85 | 71.4 | 1.8 |
YOLOv5n + C3SE | 37 | 91.8 | 78.2 | 82.5 | 52 | 85.1 | 71.6 | 1.69 |
