Image Classification on STL10 original (test)
98.31AccuracyC8-Aug.
Evaluation Results
| Method | Links | |
|---|---|---|
| C8-Aug.Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 98.31 | |
| VanillaBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 98.31 | |
| VanillaBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 98.3 | |
| Rotation AugmentationBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 98.08 | |
| Rotation AugmentationBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 97.85 | |
| C8-Aug.Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 97.83 | |
| Prior-Regularized LCBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 97.01 | |
| Prior-Regularized LCBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 96.15 | |
| Learned Canonicalization (LC)Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 95.3 | |
| Learned Canonicalization (LC)Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 95.11 | |
| SESN-B#Params=11M2026.03 | 91.49 | |
| Harm-WideResNet#Params=11M2026.03 | 90.45 | |
| GaussDerResNet (with LS)#Params=2.1M, label smoothing=true2026.03 | 89.36 | |
| WideResNet#Params=11M2026.03 | 88.52 | |
| GaussDerResNet (no LS)#Params=2.1M, label smoothing=false2026.03 | 88.05 |