Image Classification on STL10 C8-augmented (test)
96.37C8-Avg AccuracyPrior-Regularized LC
Evaluation results
| Method | Links | |
|---|---|---|
| Prior-Regularized LCBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 96.37 | |
| C8-Aug.Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 96.31 | |
| Prior-Regularized LCBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 95.73 | |
| Rotation AugmentationBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 94.97 | |
| Learned Canonicalization (LC)Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 94.67 | |
| C8-Aug.Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 94.45 | |
| Rotation AugmentationBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 94.07 | |
| Learned Canonicalization (LC)Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 93.92 | |
| VanillaBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 76.66 | |
| VanillaBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 73.87 |