Image Classification on CIFAR100 C8-augmented (test)
83.61C8 Average AccuracyPrior-Regularized LC
Evaluation Results
| Method | Links | |
|---|---|---|
| Prior-Regularized LCBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 83.61 | |
| Prior-Regularized LCBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 82.09 | |
| Learned Canonicalization (LC)Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 80.48 | |
| C8-Aug.Backbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 80.08 | |
| C8-Aug.Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 79.72 | |
| Rotation AugmentationBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 78.39 | |
| Learned Canonicalization (LC)Backbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 77.52 | |
| Rotation AugmentationBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 74.12 | |
| VanillaBackbone=ViT-Base, Pre-training=ImageNet-1K2023.10 | 55.87 | |
| VanillaBackbone=ResNet50, Pre-training=ImageNet-1K2023.10 | 44.86 |