ShakeDrop regularization
ShakeDrop regularization
复制标题
DOI：
--
复制
发表时间：
2018-02
期刊：
影响因子：
--
通讯作者：
Yoshihiro Yamada;M. Iwamura;K. Kise
中科院分区：
文献类型：
--
作者：
Yoshihiro Yamada;M. Iwamura;K. Kise
本文提出了一种强大的正则化方法，称为\textit{ShakeDrop正则化}。ShakeDrop受到Shake-Shake正则化的启发，通过干扰学习来降低错误率。虽然Shake-Shake只能应用于具有多个分支的ResNeXt，但ShakeDrop不仅可以应用于ResNeXt，还可以以内存有效的方式应用于ResNet，Wide ResNet和PyramidNet。ShakeDrop的重要和有趣的特性是，它通过在前向训练过程中将负因子乘以卷积层的输出来强烈干扰学习。ShakeDrop的有效性通过CIFAR-10/100和Tiny ImageNet数据集上的实验得到了证实。
This paper proposes a powerful regularization method named \textit{ShakeDrop regularization}. ShakeDrop is inspired by Shake-Shake regularization that decreases error rates by disturbing learning. While Shake-Shake can be applied to only ResNeXt which has multiple branches, ShakeDrop can be applied to not only ResNeXt but also ResNet, Wide ResNet and PyramidNet in a memory efficient way. Important and interesting feature of ShakeDrop is that it strongly disturbs learning by multiplying even a negative factor to the output of a convolutional layer in the forward training pass. The effectiveness of ShakeDrop is confirmed by experiments on CIFAR-10/100 and Tiny ImageNet datasets.