Fast AutoAugment

Open paper
Benchmark Model Rank Results
image-classification-on-svhnWide-ResNet-28-10 (Fast AA)#2Percentage error: 1.1
data-augmentation-on-imagenetResNet-200 (Fast AA)#4Accuracy (%): 80.6
data-augmentation-on-imagenetResNet-50 (Fast AA)#13Accuracy (%): 77.6
image-classification-on-cifar-10PyramidNet+ShakeDrop (Fast AA)#60Percentage correct: 98.3
image-classification-on-cifar-100PyramidNet+ShakeDrop (Fast AA)#61Percentage correct: 88.3
image-classification-on-imagenetResNet-200 (Fast AA)#731Top 1 Accuracy: 80.6%
image-classification-on-imagenetResNet-50 (Fast AA)#905Top 1 Accuracy: 77.6%

Rank counts only results with a code link.