期刊
COMPUTER VISION - ECCV 2016, PT VII
卷 9911, 期 -, 页码 467-482出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-46478-7_29
关键词
Relay Backpropagation; Convolutional neural networks; Large scale image classification
Learning deeper convolutional neural networks has become a tendency in recent years. However, many empirical evidences suggest that performance improvement cannot be attained by simply stacking more layers. In this paper, we consider the issue from an information theoretical perspective, and propose a novel method Relay Backpropagation, which encourages the propagation of effective information through the network in training stage. By virtue of the method, we achieved the first place in ILSVRC 2015 Scene Classification Challenge. Extensive experiments on two large scale challenging datasets demonstrate the effectiveness of our method is not restricted to a specific dataset or network architecture.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据