Table 3.
Performance of various residual networks on preening detection.
| ResNet | MIOU (%) | Precision (%) | Recall (%) | Specificity (%) | Accuracy (%) | F1 Score (%) | AP (%) | Processing Speed (ms·image−1) |
|---|---|---|---|---|---|---|---|---|
| ResNet18 | 87.4 | 87.2 | 87.1 | 96.7 | 94.7 | 87.1 | 83.6 | 364.8 |
| ResNet34 | 87.4 | 88.5 | 86.2 | 97.0 | 94.8 | 87.3 | 83.1 | 378.4 |
| ResNet50 | 87.8 | 84.4 | 85.3 | 95.7 | 93.5 | 84.9 | 81.4 | 342.9 |
| ResNet101 | 87.4 | 87.7 | 88.4 | 96.7 | 95.0 | 88.1 | 83.5 | 386.0 |
| ResNet152 | 87.4 | 83.1 | 90.1 | 95.1 | 94.1 | 86.5 | 85.7 | 387.7 |
| ResNet1000 | 87.4 | 84.5 | 90.8 | 95.6 | 94.6 | 87.6 | 85.6 | 393.2 |
Note: ResNet is residual network; ResNet18-ResNet1000 is the ResNet with 18–1000 layers; MIOU is mean intersection over union; and AP is average precision.