Table 10 Performance comparison of the fine-tuned EfficientNet-B0 model with and without class weighting.
Class / metric | With class weighting | Without class weighting | ||||
|---|---|---|---|---|---|---|
Precision | Recall | F1 Score | Precision | Recall | F1 Score | |
Apple Scab | 0.98 | 1.00 | 0.99 | 1.00 | 0.60 | 0.75 |
Black Rot | 1.00 | 1.00 | 1.00 | 1.00 | 0.65 | 0.78 |
Cedar Apple Rust | 1.00 | 0.96 | 0.98 | 0.83 | 0.71 | 0.77 |
Healthy | 1.00 | 1.00 | 1.00 | 0.76 | 1.00 | 0.87 |
Macro Avg F1 Score | 0.99 | 0.79 | ||||
Model-level Accuracy | 99.69% | 82.70% | ||||
