Efficient Vits On Imagenet 1K With Lv Vit S
評価指標
GFLOPs
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 | GFLOPs | Top 1 Accuracy |
|---|---|---|
| multi-criteria-token-fusion-with-one-step | 3.6 | 82.3 |
| multi-criteria-token-fusion-with-one-step | 4.9 | 83.5 |
| dynamicvit-efficient-vision-transformers-with | 4.6 | 83.0 |
| token-labeling-training-a-85-5-top-1-accuracy | 6.6 | 83.3 |
| joint-token-pruning-and-squeezing-towards | 3.8 | 82.5 |
| spvit-enabling-faster-vision-transformers-via | 4.3 | 83.1 |
| dynamicvit-efficient-vision-transformers-with | 5.1 | 83.2 |
| not-all-patches-are-what-you-need-expediting | 3.9 | 82.5 |
| patch-slimming-for-efficient-vision | 4.5 | 82.9 |
| patch-slimming-for-efficient-vision | 4.7 | 82.4 |
| diffrate-differentiable-compression-rate-for | 3.9 | 82.6 |
| multi-criteria-token-fusion-with-one-step | 4.2 | 83.4 |
| adaptive-sparse-vit-towards-learnable | 3.9 | 82.6 |
| not-all-patches-are-what-you-need-expediting | 4.7 | 83.0 |
| adaptive-sparse-vit-towards-learnable | 4.6 | 83.1 |
| joint-token-pruning-and-squeezing-towards | 3.8 | 82.6 |
| beyond-attentive-tokens-incorporating-token | 4.7 | 83.1 |
| ppt-token-pruning-and-pooling-for-efficient | 4.6 | 83.1 |
| dynamicvit-efficient-vision-transformers-with | 5.8 | 83.3 |