Table 5 The impact of different attention mechanisms on network performance.
From: A new method for Tomicus classification of forest pests based on improved ResNet50 algorithm
Num | ResNet50 | Other modules | Attention mechanism | Accuracy | Params | ||||
|---|---|---|---|---|---|---|---|---|---|
ECA | SE | CBAM | MLCA | MSCAM | |||||
1 | ✓ | ✓ | ✓ | 92.8% | 1.6M | ||||
2 | ✓ | ✓ | ✓ | 91.4% | 1.5 M | ||||
3 | ✓ | ✓ | ✓ | 91.4% | 2.7 M | ||||
4 | ✓ | ✓ | ✓ | 90.1% | 1.7 M | ||||
5 | ✓ | ✓ | ✓ | 89.7% | 1.9 M | ||||
