Year: 2019
Type: article
Abstract: 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.
Source: IEEE Access
Institutions: Osaka Prefecture University, Preferred Networks (Japan)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,750
Awards: Promotion of learning process of deep learning by interference, G3170821105, 一般物体認識における不正確な重みの更新がもたらす効果の分析と時系列データへの拡張, Assistance for People with Visual Impairment by Recognizing Surrounding Information Using an Omnidirectional Camera, G5786559832, G6718509927, Construction of Knowledge Log Based on Activity Analysis and Its Applications
OpenAlex ID: W2903105043
