CASIA OpenIR  > 类脑智能研究中心  > 微观重建与智能分析
A Refined Spatial Transformer Network
Shu, Chang1,2; Chen, Xi2; Yu, Chong2,3; Han, Hua2,4,5
2018
会议名称International Conference on Neural Information Processing (ICONIP 2018)
页码151-161
会议日期13-16 December, 2018
会议地点Siem Reap, Cambodia
出版者Springer
摘要

Spatial invariance to geometrically distorted data is of great importance in the vision and learning communities. Spatial transformer network (STN) can solve this problem in a computationally efficient manner. STN is a differentiable module which can be inserted in a standard CNN architecture to achieve spatial transformation of data. STN and its variants can handle global deformation well, but lack the ability to deal with local spatial variation. Hence how to achieve a better manner of spatial transformation within a neural network becomes a pressing matter of the moment. To address this issue, we design a module to estimate the difference between the ground truth and STN output. The difference is measured in the form of motion field. The motion field is utilized to refine the spatial transformation predicted by STN. Experimental results reveal that our method outperforms the state-of-the-art methods in the cluttered MNIST handwritten digits classification task and planar image alignment task.

关键词Spatial invariance Geometrical distortion Spatial transformer networks Motion field Refined spatial transformer network
DOIhttps://doi.org/10.1007/978-3-030-04182-3_14
收录类别EI
语种英语
引用统计
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/21724
专题类脑智能研究中心_微观重建与智能分析
通讯作者Han, Hua
作者单位1.University of Chinese Academy of Sciences, Beijing, China
2.Institute of Automation, Chinese Academy of Sciences, Beijing, China
3.The Faculty of Mathematics and Statistics, Hubei University, Wuhan, China
4.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China
5.School of Future Technology, University of Chinese Academy of Sciences, Beijing, China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Shu, Chang,Chen, Xi,Yu, Chong,et al. A Refined Spatial Transformer Network[C]:Springer,2018:151-161.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A+Refined+Spatial+Tr(1085KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Shu, Chang]的文章
[Chen, Xi]的文章
[Yu, Chong]的文章
百度学术
百度学术中相似的文章
[Shu, Chang]的文章
[Chen, Xi]的文章
[Yu, Chong]的文章
必应学术
必应学术中相似的文章
[Shu, Chang]的文章
[Chen, Xi]的文章
[Yu, Chong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A+Refined+Spatial+Transformer+Network.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。