ImageNet-V2 Dataset
family | model | params (m) | pretrain | finetune | GFLOPs | Top-1 |
---|---|---|---|---|---|---|
DeiT III | ViT-H (DeiT III) | 632.1 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 167.4 | 79.2 |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-22k : Sup. : 90 | IN-1k : 50 : 384 | 191.2 | 79.1 |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 61.6 | 78.6 |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-22k : Sup. : 90 | IN-1k : 50 : 384 | 55.5 | 77.9 |
ConvNeXt | ConvNeXt-XL | 350.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 179.0 | 77.7 |
ConvNeXt | ConvNeXt-L | 198.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 101.0 | 77.7 |
Swin | Swin-L | 197.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 103.9 | 77.0 |
ConvNeXt | ConvNeXt-XL | 350.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 60.9 | 77.0 |
TransNeXt | TransNeXt-B | 89.7 | IN-1k : Sup. : 300 | IN-1k : 5 : 384 | 56.3 | 77.0 |
TransNeXt | TransNeXt-S | 49.7 | IN-1k : Sup. : 300 | IN-1k : 5 : 384 | 32.1 | 76.8 |
ConvNeXt | ConvNeXt-B | 89.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 45.1 | 76.6 |
ConvNeXt | ConvNeXt-L | 198.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 34.4 | 76.6 |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 191.2 | 76.6 |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 17.6 | 76.5 |
Swin | Swin-L | 197.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 34.5 | 76.3 |
Swin | Swin-B | 88.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 47.0 | 76.3 |
DeiT III | ViT-H (DeiT III) | 632.1 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 167.4 | 75.9 |
ConvNeXt | ConvNeXt-B | 89.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 15.4 | 75.6 |
ConvNeXt | ConvNeXt-L | 198.0 | IN-1k : Sup. : 300 | IN-1k : 30 : 384 | 101.0 | 75.3 |
TransNeXt | TransNeXt-B | 89.7 | IN-1k : Sup. : 300 | — : — : — | 18.4 | 75.1 |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 61.6 | 75.1 |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 55.5 | 74.8 |
TransNeXt | TransNeXt-S | 49.7 | IN-1k : Sup. : 300 | — : — : — | 10.3 | 74.8 |
ConvNeXt | ConvNeXt-B | 89.0 | IN-1k : Sup. : 300 | IN-1k : 30 : 384 | 45.0 | 74.7 |
Swin | Swin-B | 88.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 15.4 | 74.6 |
ConvNeXt | ConvNeXt-L | 198.0 | IN-1k : Sup. : 300 | — : — : — | 34.4 | 74.0 |
TransNeXt | TransNeXt-T | 28.2 | IN-1k : Sup. : 300 | — : — : — | 5.7 | 73.8 |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 4.6 | 73.8 |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 17.5 | 73.6 |
ConvNeXt | ConvNeXt-B | 89.0 | IN-1k : Sup. : 300 | — : — : — | 15.4 | 73.4 |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 15.5 | 73.1 |
TransNeXt | TransNeXt-Micro | 12.8 | IN-1k : Sup. : 300 | — : — : — | 2.7 | 72.6 |
Swin | Swin-S | 50.0 | IN-1k : Sup. : 300 | — : — : — | 8.7 | 71.8 |
ResNet (RSB) | ResNet-152 (RSB) | 60.2 | IN-1k : Sup. : 600 | — : — : — | 11.6 | 70.6 |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 4.6 | 70.5 |
ResNet (RSB) | ResNet-101 (RSB) | 44.5 | IN-1k : Sup. : 600 | — : — : — | 7.9 | 70.3 |
Swin | Swin-T | 29.0 | IN-1k : Sup. : 300 | — : — : — | 4.5 | 69.5 |
ResNet (RSB) | ResNet-50 (RSB) | 25.6 | IN-1k : Sup. : 600 | — : — : — | 4.1 | 68.7 |
ResNet (RSB) | ResNet-34 (RSB) | 21.8 | IN-1k : Sup. : 600 | — : — : — | 3.7 | 65.1 |
ResNet (RSB) | ResNet-18 (RSB) | 11.7 | IN-1k : Sup. : 600 | — : — : — | 1.8 | 59.4 |
family | model | params (m) | pretrain | finetune | gflops | top-1 | top-5 |
---|---|---|---|---|---|---|---|
DeiT III | ViT-H (DeiT III) | 632.1 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 167.4 | 79.2 | — |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-22k : Sup. : 90 | IN-1k : 50 : 384 | 191.2 | 79.1 | — |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 61.6 | 78.6 | — |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-22k : Sup. : 90 | IN-1k : 50 : 384 | 55.5 | 77.9 | — |
ConvNeXt | ConvNeXt-L | 198.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 101.0 | 77.7 | — |
ConvNeXt | ConvNeXt-XL | 350.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 179.0 | 77.7 | — |
TransNeXt | TransNeXt-B | 89.7 | IN-1k : Sup. : 300 | IN-1k : 5 : 384 | 56.3 | 77.0 | — |
ConvNeXt | ConvNeXt-XL | 350.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 60.9 | 77.0 | — |
Swin | Swin-L | 197.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 103.9 | 77.0 | — |
TransNeXt | TransNeXt-S | 49.7 | IN-1k : Sup. : 300 | IN-1k : 5 : 384 | 32.1 | 76.8 | — |
ConvNeXt | ConvNeXt-L | 198.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 34.4 | 76.6 | — |
ConvNeXt | ConvNeXt-B | 89.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 45.1 | 76.6 | — |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 191.2 | 76.6 | — |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 17.6 | 76.5 | — |
Swin | Swin-B | 88.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 384 | 47.0 | 76.3 | — |
Swin | Swin-L | 197.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 34.5 | 76.3 | — |
DeiT III | ViT-H (DeiT III) | 632.1 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 167.4 | 75.9 | — |
ConvNeXt | ConvNeXt-B | 89.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 15.4 | 75.6 | — |
ConvNeXt | ConvNeXt-L | 198.0 | IN-1k : Sup. : 300 | IN-1k : 30 : 384 | 101.0 | 75.3 | — |
TransNeXt | TransNeXt-B | 89.7 | IN-1k : Sup. : 300 | — : — : — | 18.4 | 75.1 | — |
DeiT III | ViT-L (DeiT III) | 304.4 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 61.6 | 75.1 | — |
TransNeXt | TransNeXt-S | 49.7 | IN-1k : Sup. : 300 | — : — : — | 10.3 | 74.8 | — |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 55.5 | 74.8 | — |
ConvNeXt | ConvNeXt-B | 89.0 | IN-1k : Sup. : 300 | IN-1k : 30 : 384 | 45.0 | 74.7 | — |
Swin | Swin-B | 88.0 | IN-22k : Sup. : 90 | IN-1k : 30 : 224 | 15.4 | 74.6 | — |
ConvNeXt | ConvNeXt-L | 198.0 | IN-1k : Sup. : 300 | — : — : — | 34.4 | 74.0 | — |
TransNeXt | TransNeXt-T | 28.2 | IN-1k : Sup. : 300 | — : — : — | 5.7 | 73.8 | — |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-22k : Sup. : 90 | IN-1k : 50 : 224 | 4.6 | 73.8 | — |
DeiT III | ViT-B (DeiT III) | 86.6 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 17.5 | 73.6 | — |
ConvNeXt | ConvNeXt-B | 89.0 | IN-1k : Sup. : 300 | — : — : — | 15.4 | 73.4 | — |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-1k : Sup. : 800 | IN-1k : 20 : 384 | 15.5 | 73.1 | — |
TransNeXt | TransNeXt-Micro | 12.8 | IN-1k : Sup. : 300 | — : — : — | 2.7 | 72.6 | — |
Swin | Swin-S | 50.0 | IN-1k : Sup. : 300 | — : — : — | 8.7 | 71.8 | — |
ResNet (RSB) | ResNet-152 (RSB) | 60.2 | IN-1k : Sup. : 600 | — : — : — | 11.6 | 70.6 | — |
DeiT III | ViT-S (DeiT III) | 22.0 | IN-1k : Sup. : 800 | IN-1k : 20 : 224 | 4.6 | 70.5 | — |
ResNet (RSB) | ResNet-101 (RSB) | 44.5 | IN-1k : Sup. : 600 | — : — : — | 7.9 | 70.3 | — |
Swin | Swin-T | 29.0 | IN-1k : Sup. : 300 | — : — : — | 4.5 | 69.5 | — |
ResNet (RSB) | ResNet-50 (RSB) | 25.6 | IN-1k : Sup. : 600 | — : — : — | 4.1 | 68.7 | — |
ResNet (RSB) | ResNet-34 (RSB) | 21.8 | IN-1k : Sup. : 600 | — : — : — | 3.7 | 65.1 | — |
ResNet (RSB) | ResNet-18 (RSB) | 11.7 | IN-1k : Sup. : 600 | — : — : — | 1.8 | 59.4 | — |