利用通用数据增强改进深度学习

Aug, 2017

Improving Deep Learning using Generic Data Augmentation

Luke Taylor, Geoff Nitschke

TL;DR该研究基于对简单的 CNN 使用几何和光度扩增方案的试验性结果，通过 4 折交叉验证考察了不同的数据扩增方案，并证明 crop 扩增在几何扩增方案中可以显著提高 CNN 任务性能。

Abstract

deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. data augmentation overcomes this iss