Image Classification On Cinic 10
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| ResNeXt29_2x64d | 91.45 | CINIC-10 is not ImageNet or CIFAR-10 | |
| efficient adaptive ensembling | 95.064 | Efficient Adaptive Ensembling for Image Classification | - |
| NAT-M2 | 94.1 | Neural Architecture Transfer | |
| ResNet-18 | 90.27 | CINIC-10 is not ImageNet or CIFAR-10 | |
| NAT-M1 | 93.4 | Neural Architecture Transfer | |
| NAT-M3 | 94.3 | Neural Architecture Transfer | |
| VGG-16 | 87.77 | CINIC-10 is not ImageNet or CIFAR-10 | |
| DenseNet-121 | 91.26 | CINIC-10 is not ImageNet or CIFAR-10 | |
| VIT-L/16 (Spinal FC, Background) | 95.80 | Reduction of Class Activation Uncertainty with Background Information |
0 of 9 row(s) selected.