RandAugment: Practical automated data augmentation with a reduced search space
Ekin D. Cubuk , Barret Zoph, Jonathon Shlens, Quoc V. Le Google Research, Brain Team {cubuk, barretzoph, shlens, Authors contributed equally.
Abstract
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 t
中文速览
深度学习图像分类中，数据增强的策略设计长期依赖人工经验，而已有的自动化方法（如AutoAugment）虽然效果好，却需要在一个小型代理任务上单独跑一轮搜索，耗时费力，而且搜到的策略并不能自动适配不同大小的模型或数据集。本文提出的RandAugment把增强策略压缩成两个直观参数——每张图片随机应用的变换数量N和全局扰动强度M，无需任何独立搜索阶段，用简单的网格搜索就能针对具体任务调参。实验表明，最优增强强度会随模型规模和数据量的变化而显著变化，这正是代理任务搜索策略的根本缺陷所在；而RandAugment在CIFAR-10/100、SVHN和ImageNet上全面持平或超越了所有此前的自动增强方法，在ImageNet上达到85.0%的准确率，比基线高1.0%，在COCO目标检测上也接近AutoAugment的最优水平。这项工作的意义在于，它把一个原本复杂、昂贵的两阶段流程变成了一个开箱即用的简单工具，让大规模采用自动数据增强真正具备了实用性。
原文 arXiv:1909.13719;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1909.13719v2