Few-shot Image Classification on CIFAR-10 Laplace1 noise 1.0 (test)
61.54AccuracyPG-DRO
Evaluation results
| Method | Links | |
|---|---|---|
| PG-DROk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 61.54 | |
| W-DROk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 60.41 | |
| SAAk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 59.56 | |
| Few-shotk (shots)=10, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 59.16 | |
| PG-DROk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 50.45 | |
| SAAk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 50.33 | |
| W-DROk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 49.34 | |
| Few-shotk (shots)=5, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 27.25 | |
| PG-DROk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 20.88 | |
| W-DROk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 20.23 | |
| SAAk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 18.81 | |
| Few-shotk (shots)=1, Backbone=ResNet-18, Pre-training Dataset=CIFAR-1002026.02 | 10.85 |