Few-shot Classification on Plant Disease 5-way 5-shot
91.52AccuracySimSiam + AugSelf
Evaluation results
| Method | Links | |
|---|---|---|
| SimSiam + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 91.52 | |
| SimSiamBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 89.94 | |
| Supervised + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 89.77 | |
| SupervisedBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 88.77 | |
| MoCo v2 + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 87.81 | |
| MoCo v2Backbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 84.98 | |
| SimSiam + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 81.14 | |
| MoCo v2 + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 78.76 | |
| SimSiamBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 75.98 | |
| MoCo v2Backbone=ResNet-18, Pre-training Dataset=STL102021.11 | 75.98 |