Image Classification on Oxford Flowers (Accuracy)
97AccuracyDeiT-L
Evaluation results
| Method | Links | |
|---|---|---|
| DeiT-LBackbone=DeiT-L, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 97 | |
| ViT-LBackbone=ViT-L, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.6 | |
| ViT-BBackbone=ViT-B, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.5 | |
| DeiT-BBackbone=DeiT-B, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.4 | |
| Swin-SBackbone=Swin-S, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.3 | |
| Swin-TiBackbone=Swin-Ti, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.2 | |
| DeiT-BBackbone=DeiT-B, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 96.1 | |
| Swin-TiBackbone=Swin-Ti, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 95.9 | |
| Swin-SBackbone=Swin-S, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 95.9 | |
| DeiT-LBackbone=DeiT-L, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 95.8 | |
| ViT-SBackbone=ViT-S, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 95.5 | |
| DeiT-SBackbone=DeiT-S, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 95.2 | |
| ViT-BBackbone=ViT-B, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 94.8 | |
| DeiT-SBackbone=DeiT-S, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 94.8 | |
| ViT-SBackbone=ViT-S, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 94.5 | |
| ViT-LBackbone=ViT-L, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 94.4 | |
| ResNet-101Backbone=ResNet-101, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 92.9 | |
| ResNet-50Backbone=ResNet-50, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 91.7 | |
| ResNet-50Backbone=ResNet-50, ForAug=true, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 91.7 | |
| ResNet-101Backbone=ResNet-101, ForAug=false, Pre-training Dataset=ImageNet, Evaluation Protocol=Finetuning2025.03 | 91.2 |