Few-shot Image Classification on CIFAR-10 Laplace2 noise (test)
59.57AccuracyPG-DRO
Evaluation results
| Method | Links | |
|---|---|---|
| PG-DROk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 59.57 | |
| SAAk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 58.93 | |
| W-DROk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 58.15 | |
| Few-shotk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 52.75 | |
| PG-DROk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 50.21 | |
| W-DROk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 49.35 | |
| SAAk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 48.03 | |
| Few-shotk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 41.38 | |
| PG-DROk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 22.28 | |
| W-DROk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 22.07 | |
| SAAk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 21.91 | |
| Few-shotk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 10.03 |