Table 1 Summarization of the existing work.
From: Multi-kernel inception-enhanced vision transformer for plant leaf disease recognition
Paper references | DL model | Dataset | Class | Accuracy (%) |
|---|---|---|---|---|
Mohanty et al.14 | AlexNet, GoogleNet | PlantVillage14 | 38 | 99.34 |
Ferentinos et al.15 | AlexNet, VGG, Overfeat, GoogleNet AlexNetOWTBn | PlantVillage14 | 58 | 99.48 |
Geetharamani et al.32 | Nine layer CNN | PlantVillage14 | 38 | 96.46 |
Chen et al.33 | VGGNet with two inception layer | Maize dataset14 | 4 | 84.25 |
Sethy et al.34 | 11 state-of-art CNN architecture with SVM for classification | Rice dataset34 | 4 | 98.38 |
Too et al.18 | Fine tune 6 different CNN models | PlantVillage14 | 38 | 99.76 |
Atila et al.19 | EfficientNet | PlantVillage14 | 38 | 99.38 |
Zeng et al.21 | Self-attention CNN with Residual Connection | AES-CD9214 MK-D2 dataset35 | 6 | 95.59 |
Qian et al.23 | Transformer and Multi- head attention | Maize dataset14 | 4 | 98.7 |
Pandey24 | DADCNN-5 | PlantVillage14 | 38 | 99.93 |
Bhujel et al.25 | CNN with Multiple attention | Tomato leaf14 | 10 | 99.69 |
Lu et al.27 | GET | GLDP12k dataset27 | 11 | 98.14 |
Yu et al.28 | ViT architecture | Ibean36 | 3 | 99.22 |
Borhani et al.29 | ViT architecture | Wheat rust37 | 3 | 100 |
Mohamed Zarboubi et al.26 | CustomBottleneck- VGGNet | PlantVillage14 | 10 | 99.12 |
Abdelaaziz Bellout et al.31 | LT-YOLOv10n | Roboflow Universe, PlantVillage14 | 9 | 98.7 |
Bellout et al.30 | Multiple YOLO architecture | PlantVillage14 PlantDoc38 | 3 | 93.1 |
