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 |
DOI | https://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 |
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