Shakedrop Regularization for Deep Residual Learning

Overfitting is a crucial problem in deep neural networks, even in the latest network architectures. In this paper, to relieve the overfitting effect of ResNet and its improvements (i.e., Wide ResNet, PyramidNet, and ResNeXt), we propose a new regularization method called ShakeDrop regularization. Sh...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.186126-186136
Main Authors: Yamada, Yoshihiro, Iwamura, Masakazu, Akiba, Takuya, Kise, Koichi
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer architecture
Computer vision
Error analysis
image classification
Interpolation
Machine learning
Network architecture
Neural networks
Perturbation methods
Random variables
Regularization
Regularization methods
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Overfitting is a crucial problem in deep neural networks, even in the latest network architectures. In this paper, to relieve the overfitting effect of ResNet and its improvements (i.e., Wide ResNet, PyramidNet, and ResNeXt), we propose a new regularization method called ShakeDrop regularization. ShakeDrop is inspired by Shake-Shake, which is an effective regularization method, but can be applied to ResNeXt only. ShakeDrop is more effective than Shake-Shake and can be applied not only to ResNeXt but also ResNet, Wide ResNet, and PyramidNet. An important key is to achieve stability of training. Because effective regularization often causes unstable training, we introduce a training stabilizer, which is an unusual use of an existing regularizer. Through experiments under various conditions, we demonstrate the conditions under which ShakeDrop works well.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2960566