RandAugment: Practical data augmentation with no separate search
RandAugment: Practical data augmentation with no separate search
E. D. Cubuk,Barret Zoph,Jonathon Shlens,Quoc V. Le
2019 · DBLP: journals/corr/abs-1909-13719
arXiv.org · 263 Citações
TLDR
RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous learned augmentation approaches on CIFAR-10, CIFar-100, SVHN, and ImageNet.