Image Classification On Imagenet V2
評価指標
Top 1 Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Top 1 Accuracy |
|---|---|
| resmlp-feedforward-networks-for-image | 69.8 |
| resmlp-feedforward-networks-for-image | 66.0 |
| when-vision-transformers-outperform-resnets | 65.5 |
| the-effectiveness-of-mae-pre-pretraining-for | 84.0 |
| levit-a-vision-transformer-in-convnet-s | 69.9 |
| going-deeper-with-image-transformers | 76.7 |
| three-things-everyone-should-know-about | 73.9 |
| moat-alternating-mobile-convolution-and | 78.4 |
| resnet-strikes-back-an-improved-training | 68.7 |
| distilling-out-of-distribution-robustness-1 | 71.7 |
| swin-transformer-v2-scaling-up-capacity-and | 78.08 |
| model-soups-averaging-weights-of-multiple | 84.22 |
| when-vision-transformers-outperform-resnets | 67.5 |
| levit-a-vision-transformer-in-convnet-s | 68.7 |
| vision-models-are-more-robust-and-fair-when | 76.2 |
| moat-alternating-mobile-convolution-and | 79.3 |
| volo-vision-outlooker-for-visual-recognition | 77.8 |
| moat-alternating-mobile-convolution-and | 80.6 |
| swin-transformer-v2-scaling-up-capacity-and | 84.00% |
| resmlp-feedforward-networks-for-image | 73.4 |
| resmlp-feedforward-networks-for-image | 74.2 |
| revisiting-weakly-supervised-pre-training-of | 81.1 |
| levit-a-vision-transformer-in-convnet-s | 71.4 |
| levit-a-vision-transformer-in-convnet-s | 63.9 |
| scaling-vision-transformers | 83.33 |
| when-vision-transformers-outperform-resnets | 69.6 |
| model-soups-averaging-weights-of-multiple | 84.63 |
| the-effectiveness-of-mae-pre-pretraining-for | 83.0 |
| moat-alternating-mobile-convolution-and | 81.5 |
| volo-vision-outlooker-for-visual-recognition | 78 |
| pali-a-jointly-scaled-multilingual-language | 84.3 |
| sequencer-deep-lstm-for-image-classification | 73.4 |
| levit-a-vision-transformer-in-convnet-s | 67.5 |