Image Classification On Tiny Imagenet 1
Metriken
Validation Acc
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Validation Acc |
|---|---|
| data-efficient-training-of-cnns-and | 91.90 |
| update-in-unit-gradient | 90.74% |
| boosting-discriminative-visual-representation | 72.18% |
| upanets-learning-from-the-universal-pixel | 67.67 |
| Modell 5 | 72.39 |
| update-in-unit-gradient | 91.02% |
| Modell 7 | 68.04 |
| automix-unveiling-the-power-of-mixup | 67.33% |
| automix-unveiling-the-power-of-mixup | 70.72% |
| ocd-learning-to-overfit-with-conditional | 90.8% |
| convolutional-xformers-for-vision | 49.56 |
| wavemix-lite-a-resource-efficient-neural-1 | 54.76 |
| vision-transformers-in-2022-an-update-on-tiny | 91.35% |
| Modell 14 | 71.56 |
| direction-concentration-learning-enhancing | 84.39% |
| mixmo-mixing-multiple-inputs-for-multiple | 70.24% |
| context-aware-compilation-of-dnn-training | 73.6% |
| densenet-models-for-tiny-imagenet | 60% |
| astroformer-more-data-might-not-be-all-you | 92.98 |
| wavemix-lite-a-resource-efficient-neural | 77.47% |
| boosting-discriminative-visual-representation | 68.89% |
| ocd-learning-to-overfit-with-conditional | 92.0% |