.png){kind=icon}
返回
Revisiting spatial dropout for regularizing convolutional neural networks
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-09054-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Overfitting is one of the most challenging problems in deep neural networks with a large number of trainable parameters. To prevent networks from overfitting, the dropout method, which is a strong regularization technique, has been widely used in fully-connected neural networks. In several state-of-the-art convolutional neural network architectures for object classification, however, dropout was partially or not even applied since its accuracy gain was relatively insignificant in most cases. Also, the batch normalization technique reduced the need for the dropout method because of its regularization effect. In this paper, we show that conventional element-wise dropout can be ineffective for convolutional layers. We found that dropout between channels in the CNNs can be functionally similar to dropout in the FCNNs, and spatial dropout can be an effective way to take advantage of the dropout technique for regularizing. To prove our points, we conducted several experiments using the CIFAR-10 and CIFAR-100 databases. For comparison, we only replaced the dropout layers with spatial dropout layers and kept all other hyperparameters and methods intact. DenseNet-BC with spatial dropout showed promising results (3.32% error rates with CIFAR-10, 3.0 M parameters) compared to other existing competitive methods.
Keyword:
Network regularization
Convolutional neural network
Spatial dropout
Deep learning
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
分享收藏Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏Imaging the Condensation and Evaporation of Molecularly Thin Films of Water with Nanometer Resolution.png)
Science
ScienceIF0
PREAI
分享收藏Viscosity of (C2–C14) 1-alkyl-3-methylimidazolium bis(trifluoromethylsulfonyl)amide ionic liquids in an extended temperature range(C2-C14) 1-烷基-3-甲基咪唑双 (三氟甲基磺酰基) 酰胺离子液体在扩展温度范围内的粘度
PREAI
分享收藏Bringing Virtualization to the x86 Architecture with the Original VMware Workstation使用原始VMware Workstation将虚拟化引入x86体系结构
OAAI
OAAI分享收藏
查看更多内容