AutoAugment: Learning Augmentation Strategies from Data
Ekin D. Cubuk , Barret Zoph , Dandelion Mané, Vijay Vasudevan, Quoc V. Le Google Brain Equal contribution.
Abstract
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
中文速览
图像分类模型依赖人工设计的数据增强策略，但这类策略费时费力且难以跨数据集迁移。AutoAugment提出用强化学习自动搜索最优数据增强策略（augmentation policy），让控制器（controller RNN）在一个包含平移、旋转、色彩调整等16种图像变换操作的搜索空间里，自动挑选操作类型、执行概率和强度的最佳组合，再用子模型在验证集上的准确率作为奖励信号反向优化控制器。实验结果表明，在CIFAR-10上错误率降至1.5%，ImageNet Top-1准确率达到83.5%，均刷新了当时的最优记录，且在SVHN等数据集上同样表现领先。更重要的是，在ImageNet上学到的增强策略可以直接迁移到Oxford Flowers、Stanford Cars等细粒度分类数据集，显著提升性能，说明自动搜索出的数据增强策略具有良好的泛化能力，为减少人工调参、提升模型泛化性能提供了一条可复用的新路径。
原文 arXiv:1805.09501;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1805.09501v3