swMATH ID: 40532
Software Authors: Ekin D. Cubuk, Barret Zoph, Jonathon Shlens, Quoc V. Le
Description: RandAugment: Practical automated data augmentation with a reduced search space. Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantially increase the computational cost. Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size. Automated augmentation policies are often found by training small models on small datasets and subsequently applied to train larger models. In this work, we remove both of these obstacles. RandAugment has a significantly reduced search space which allows it to be trained on the target task with no need for a separate proxy task. Furthermore, due to the parameterization, the regularization strength may be tailored to different model and dataset sizes. RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous automated augmentation approaches on CIFAR-10/100, SVHN, and ImageNet. On the ImageNet dataset we achieve 85.0
Homepage: https://arxiv.org/abs/1909.13719
Source Code:  https://github.com/fastai/timmdocs/tree/master/
Related Software: FixMatch; CIFAR; MixMatch; mixup; ImageNet; Python; SGDR; PyTorch; ReMixMatch; AugMix; BBN; CReST; Semi-iNat; BiSTF; FlexMatch; T2T-ViT; CutMix; CBAM; ECA-Net; EfficientNet
Cited in: 1 Document

Cited in 1 Serial

1 Machine Learning

Citations by Year