Table 11 Performance comparison of the proposed model with existing work on PlantVillage dataset14.
From: Multi-kernel inception-enhanced vision transformer for plant leaf disease recognition
Paper Ref. | DL model used | No of class | Performance | Parameter |
|---|---|---|---|---|
Mohanthy et al.14 | Transfer learning (GoogleNet) | 38 | 99.34 | 6.7M |
Ferentinos et al.15 | Transfer Learning (VGG16, Overfeat) | 58 | 99.53 | 138.4M |
Waheed et al.46 | Dense CNN | 3 | 98.06 | NA |
Pandey et al.24 | DADCNN-5 | 38 | 99.93 | NA |
Fang et al.47 | ResNet-50 | 10 | 95.61 | 25.6M |
Thakur et al.16 | VGG-ICNN | NA | 99.16 | 6M |
I Kunduracioglu48 | EfficientNetV2_m | 4 | 100 | 54.4M |
I Kunduracioglu49 | Res2Next50 | 10 | 99.85 | NA |
Dheeraj et al.17 | LWDN | NA | 99.37 | 1.5M |
I Kunduracioglu et al.50 | CNN with ViT | 4 | 100 | NA |
Proposed | Inception-Enhanced ViT | 7 | 99.41 | 0.90M |
