Table 1 Comparison of different models on the tomato leaf disease dataset
From: DWTFormer: a frequency-spatial features fusion model for tomato leaf disease identification
Models | Accuracy/% | Precision/% | Recall/% | F1-score/% | Parameters/M | FLOPs/G |
|---|---|---|---|---|---|---|
MobileNet V3-Large | 92.99 | 93.24 | 92.96 | 93.00 | 5.40 | 6.19 |
Swin Transformer-Base | 85.03 | 85.10 | 85.00 | 84.90 | 88.00 | 15.40 |
PVTv2-B/3 | 86.56 | 87.11 | 86.51 | 86.68 | 45.20 | 6.90 |
Vit-Base | 87.48 | 87.69 | 87.52 | 87.45 | 86.00 | 55.40 |
Mixer-B/16 | 84.42 | 84.83 | 84.36 | 84.42 | 59.00 | 11.60 |
DWTFormer | 99.28 | 99.10 | 99.18 | 99.10 | 33.69 | 7.96 |