Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks | |
Shen, Li ; Lin, Zhouchen ; Huang, Qingming | |
2016 | |
关键词 | Relay Backpropagation Convolutional neural networks Large scale image classification |
英文摘要 | 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.; CPCI-S(ISTP); lishen@robots.ox.ac.uk; zlin@pku.edu.cn; qmhuang@ucas.ac.cn; 467-482; 9911 |
语种 | 英语 |
出处 | 14th European Conference on Computer Vision (ECCV) |
DOI标识 | 10.1007/978-3-319-46478-7_29 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/460047] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Shen, Li,Lin, Zhouchen,Huang, Qingming. Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论