Image Classification on ImageNet-1K (test) (Top-1 and Top-5 Accuracy)
84.9Top-1 AccuracyDilateFormer-B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DilateFormer-BSize=224², Train=120, Params=48M, FLOPs=9.96G2024.07 | 84.9 | — | |
| iiANET-LSize=299², Train=120, Params=50.9M, FLOPs=13.45G2024.07 | 84.9 | 96.83 | |
| CoAtNet-3Size=224², Train=90, Params=168M, FLOPs=32.53G2024.07 | 84.5 | — | |
| BoT50Size=256², Train=90, Params=25.6M, FLOPs=3.18G2024.07 | 84.4 | — | |
| EffNet-B5Size=224², Train=90, Params=30.4M, FLOPs=4.49G2024.07 | 83.6 | 96.7 | |
| Next-ViT-BSize=224², Train=300, Params=44.8M, FLOPs=8.3G2024.07 | 83.2 | — | |
| VMamba-TSize=224², Train=90, Params=30M, FLOPs=4.9G2024.07 | 82.6 | — | |
| CvT-21Size=224², Train=300, Params=32M, FLOPs=7.1G2024.07 | 82.5 | — | |
| Cross-ViT-BSize=224², Train=120, Params=105M, FLOPs=20.1G2024.07 | 82.2 | — | |
| DeiT-BSize=224², Train=120, Params=86M, FLOPs=17.5G2024.07 | 81.8 | — | |
| Swin-TSize=224², Train=300, Params=29M, FLOPs=4.5G2024.07 | 81.3 | — | |
| S4ND-ViT-BSize=224², Train=90, Params=89M, FLOPs=17.1G2024.07 | 80.4 | — | |
| Vim-SSize=224², Train=90, Params=26M, FLOPs=5.3G2024.07 | 80.3 | — | |
| iiANET-BSize=299², Train=90, Params=25.2M, FLOPs=8.22G2024.07 | 79.34 | 94.71 | |
| ResNet-101Size=224², Train=90, Params=44.5M, FLOPs=14.58G2024.07 | 78 | 94 | |
| Dense201Size=224², Train=90, Params=20.0M, FLOPs=7.35G2024.07 | 77.42 | 93.6 | |
| MobileViT-SSize=256², Train=90, Params=6M, FLOPs=2G2024.07 | 77 | 94.6 | |
| ViT-L/16Size=224², Train=150, Params=304.3M, FLOPs=59.69G2024.07 | 76.53 | 93.2 |