Fast AutoAugment

NeurIPS 2019 Sungbin LimIldoo KimTaesup KimChiheon KimSungwoong Kim

Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 PyramidNet+ShakeDrop (Fast AA) Percentage correct 98.3 # 8
Image Classification CIFAR-100 PyramidNet+ShakeDrop (Fast AA) Percentage correct 88.3 # 7
Image Classification ImageNet ResNet-200 (Fast AA) Top 1 Accuracy 80.6% # 57
Top 5 Accuracy 95.3% # 37
Image Classification ImageNet ResNet-50 (Fast AA) Top 1 Accuracy 77.6% # 95
Top 5 Accuracy 95.3% # 37
Image Classification SVHN Wide-ResNet-28-10 (Fast AA) Percentage error 1.1 # 2

Methods used in the Paper