Image Classification on ImageNet Real 1.0 (test)
91.2Top-1 AccuracyViTAE-H
Evaluation results
| Method | Links | |
|---|---|---|
| ViTAE-H#Params=644 M, Test size=512, Pre-training/Method=MAE2022.02 | 91.2 | |
| ViTAE-L#Params=311 M, Test size=384, Pre-training/Method=MAE, Fine-tuned on ImageNet-22K=true2022.02 | 91.1 | |
| ViTAE-L#Params=311 M, Test size=224, Pre-training/Method=MAE, Fine-tuned on ImageNet-22K=true2022.02 | 90.8 | |
| ViTAE-H#Params=644 M, Test size=448, Pre-training/Method=MAE, Fine-tuned on ImageNet-22K=true2022.02 | 90.8 | |
| ViTAE-H#Params=644 M, Test size=224, Pre-training/Method=MAE, Fine-tuned on ImageNet-22K=true2022.02 | 90.7 | |
| ViTAE-L#Params=311 M, Test size=224, Pre-training/Method=MAE2022.02 | 90.3 | |
| ViT-L#Params=304 M, Test size=224, Pre-training/Method=MAE, Re-implemented=true2022.02 | 90.1 | |
| Swin-L#Params=197 M, Test size=384, Pre-training/Method=Supervised, Fine-tuned on ImageNet-22K=true2022.02 | 90 | |
| ViTAE-B#Params=89 M, Test size=224, Pre-training/Method=MAE, Fine-tuned on ImageNet-22K=true2022.02 | 89.9 | |
| ViTAE-B#Params=89 M, Test size=224, Pre-training/Method=MAE2022.02 | 89.4 | |
| ViT-B#Params=88 M, Test size=224, Pre-training/Method=MAE, Re-implemented=true2022.02 | 89.1 | |
| T2T-ViT-24#Params=65 M, Test size=224, Pre-training/Method=Supervised2022.02 | 87.2 |