Image Classification on Oxford Flowers-102 (val)
98.9Top-1 AccuracyDeiT III-L
Evaluation results
| Method | Links | |
|---|---|---|
| DeiT III-LBackbone=ViT-L, Pre-training=ImageNet-1k, Epochs=400, Resolution=224x224, Crop ratio=1.02022.04 | 98.9 | |
| DeiT III-BBackbone=ViT-B, Pre-training=ImageNet-1k, Epochs=400, Resolution=224x224, Crop ratio=1.02022.04 | 98.6 | |
| DeiT-BPre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 98.4 | |
| Grafit ResNet-50 [52]Pre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 98.2 | |
| DeiT III-SBackbone=ViT-S, Pre-training=ImageNet-1k, Epochs=400, Resolution=224x224, Crop ratio=1.02022.04 | 96.4 | |
| ViT-B/16 [42]Pre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 96 | |
| ViT-L/16 [42]Pre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 91.4 | |
| ViT-L/16 [13]Pre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 89.7 | |
| ViT-B/16 [13]Pre-training=ImageNet-1k, Crop ratio=0.8752022.04 | 89.5 |