Japanese / English


論文の言語 英語
著者 Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba and Koichi Kise
論文名 ShakeDrop Regularization for Deep Residual Learning
論文誌名 IEEE Access
Vol. 7
No. 1
ページ pp.186126-186136
年月 2019年12月
要約 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.
DOI 10.1109/ACCESS.2019.2960566