arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.09501cs.CVcs.LGstat.ML
收藏

AutoAugment:从数据中学习增强策略

AutoAugment: Learning Augmentation Policies from Data

Google Brain(谷歌大脑)

Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le

摘要:

数据增强是提高现代图像分类器精度的有效技术。然而,当前的数据增强实现是手动设计的。在本文中,我们描述了一个简单的过程,称为AutoAugment自动搜索改进的数据增强政策。在我们的实现中,我们设计了一个搜索空间,其中一个策略由许多子策略组成,其中一个是随机选择的每个小批量中的每个图像。子策略由两个操作组成,每个操作是诸如平移、旋转或剪切的图像处理功能,以及应用这些功能的概率和幅度。我们使用搜索算法来找到最佳策略,使得神经网络在目标数据集上产生最高的验证精度。我们的方法在CIFAR-10、CIFAR-100、SVHN和ImageNet上实现了最先进的准确性(无需额外数据)。在ImageNet上,我们获得了83.5%的Top-1准确率,比之前的83.1%高出0.4%。在CIFAR-10上,我们实现了1.5%的出错率,比以前的最先进的增强策略高出0.6%。我们发现增强策略在数据集之间是可转移的。在ImageNet上学习的策略可以很好地转移到其他数据集上,例如Oxford Flowers,Caltech-101,Oxford-IIT Pets,FGVC Aircraft和Stanford Cars。

英文摘要:

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-the-art. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑