Figure 1.
Figure 2.
Figure 3.
Figure 4.
Figure 5.
Figure 6.
Figure 7.
Figure 8.
Film Damage Classification and Identification Results of CBAM-ResNet50 Model
| Damage category | Accuracy (%) | Accuracy (%) | Recall (%) | F1 Fraction |
|---|---|---|---|---|
| Crack | 95.02 | 95.99 | 96.69 | 96.34 |
| Dewetting | 96.21 | 96.78 | 96.49 | |
| Particles | 93.98 | 91.90 | 92.93 | |
| Scratches | 88.01 | 85.98 | 86.98 |
Steel Defect Classification and Identification Results of CBAM-ResNet50 Model
| Damage category | Accuracy (%) | Accuracy (%) | Recall (%) | F1 Fraction |
|---|---|---|---|---|
| Press-in of scale | 95.56 | 96.67 | 96.67 | 96.67 |
| Patch | 93.33 | 93.33 | 93.33 | |
| Cracking | 96.67 | 96.67 | 96.67 | |
| Pit | 96.67 | 96.67 | 96.67 | |
| Impurities | 93.33 | 93.33 | 93.33 | |
| scratches | 96.67 | 96.67 | 96.67 |
Four CBAM Attention Mechanism Addition Schemes
| Programmer | Attention mechanism adding method |
|---|---|
| Option 1 | Add an attention mechanism after the first convolution layer |
| Option 2 | Two attention mechanisms are added after the first and last convolution layer |
| Option 3 | Add 1 attention mechanism after the last convolutional layer |
| Option 4 | Do not add attention mechanism |
Ablation experiments on a test set of self-made film damage images
| Original model | Transfer learning | CBAM Protocol 1 | CBAM Scheme 2 | CBAM Scheme 3 | CBAM Protocol 4 | AlphaDrop out +SeLU | AlphaDrop out+ReLU | Accuracy (%) |
|---|---|---|---|---|---|---|---|---|
| ✓ | 65 | |||||||
| ✓ | ✓ | 85.04 | ||||||
| ✓ | ✓ | 85.06 | ||||||
| ✓ | ✓ | 85.12 | ||||||
| ✓ | ✓ | 85.09 | ||||||
| ✓ | ✓ | 85.08 | ||||||
| ✓ | ✓ | 85.17 | ||||||
| ✓ | ✓ | 85.13 | ||||||
| ✓ | ✓ | ✓ | 85.69 | |||||
| ✓ | ✓ | ✓ | 89.16 | |||||
| ✓ | ✓ | ✓ | 86.45 | |||||
| ✓ | ✓ | ✓ | 85.04 | |||||
| ✓ | ✓ | ✓ | ✓ | 90.58 | ||||
| ✓ | ✓ | ✓ | ✓ | 90.45 |
Performance comparison of CBAM-ResNet50 model under different activation functions
| Activation function | Classification accuracy (%) |
|---|---|
| AlphaDropout+SeLU | 90.58 |
| AlphaDropout+ReLU | 90.45 |
| ReLU | 89.16 |
Film Damage Classification Performance of Different Models
| Model | Test Set Accuracy (%) | Training time (H) | Number of parameters |
|---|---|---|---|
| AlexNet | 63.28 | 57 | 57.02×106 |
| GoogLeNet | 60.59 | 42 | 46.88×106 |
| VGG16 | 70.02 | 135 | 130.38×106 |
| VGG19 | 67.19 | 142 | 139.59×106 |
| ResNet18 | 64.32 | 21 | 21.80×106 |
| ResNet50 | 65.01 | 25 | 25.56×106 |
| ResNet101 | 64.57 | 41 | 44.55×106 |
| CBAM-ResNet50 | 90.58 | 23 | 23.48×106 |