Table 8 Performance comparison of the proposed model with standard DL models under similar training conditions on PlantVillage Dataset.
From: Multi-kernel inception-enhanced vision transformer for plant leaf disease recognition
Models | Accuracy (%) | Precision (%) | Recall (%) | F1-score (%) | Parameter (M) | Size (MB) | FLOPs (B) |
|---|---|---|---|---|---|---|---|
VGG16 | 95.65 | 95.54 | 95.72 | 95.62 | 138.4 | 527.79 | 31.04 |
VGG19 | 98.87 | 98.23 | 98.45 | 98.34 | 143.7 | 548.05 | 39.38 |
InceptionV3 | 97.27 | 97.31 | 97.28 | 97.29 | 23.9 | 103.61 | 5.72 |
ResNet50 | 97.98 | 97.68 | 97.82 | 97.75 | 25.6 | 97.49 | 8.26 |
EfficientNetB0 | 99.62 | 99.66 | 99.63 | 99.45 | 5.3 | 20.17 | 820.4 |
MobileNetV2 | 93.52 | 93.23 | 93.48 | 93.35 | 3.5 | 13.37 | 640.6 |
Inception Enhanced VIT | 99.42 | 99.27 | 99.34 | 99.30 | 0.90 | 3.72 | 29.34 |
