STDIN: Spatio-temporal distilled interpolation for electron microscope images
文献类型:期刊论文
作者 | Wang, Zejin2,4; Sun, Guodong2,4; Li, Guoqing4; Shen, Lijun4; Zhang, Lina4; Han, Hua1,3,4 |
刊名 | NEUROCOMPUTING |
出版日期 | 2022-09-21 |
卷号 | 505页码:188-202 |
ISSN号 | 0925-2312 |
关键词 | Spatio-temporal ensemble Feedback distillation Electron microscope interpolation |
DOI | 10.1016/j.neucom.2022.07.037 |
通讯作者 | Han, Hua(hua.han@ia.ac.cn) |
英文摘要 | Recently, flow-based approaches have shown considerable success in interpolating video images. However, in contrast to video images, electron microscope (EM) images are further complex due to noise and severe deformation between consecutive sections. Consequently, conventional flow-based interpola-tion algorithms, which assume a single offset per position, are not able to robustly model the movement of such complicated data. To address the aforementioned problems, this study propose a novel EM image interpolation framework that accommodates a range of offsets per location and further distills the inter-mediate features. First, a spatio-temporal ensemble (STE) interpolation module for capturing the missing middle features is presented. The STE is subdivided into two modules: temporal interpolation and resid-ual spatial-correlated block (RSCB). The former predicts the intermediate features in two directions with several offsets at each location. Moreover, the RSCB uses the correlation coefficients for aggregated sam-pling. Thus, even if intermediate features are severely deformed, the STE effectively improves their accu-racy. Second, a stackable feedback distillation block (SFDB) is introduced, which enhances the quality of intermediate features by distilling them from the input, and interpolated images, using a feedback mech-anism. Extensive experiments demonstrate that the proposed method presents a superior performance compared with previous studies, both quantitatively and qualitatively.(c) 2022 Elsevier B.V. All rights reserved. |
资助项目 | National Science and Technol-ogy Innovation 2030 Major Program[XDA16021104] ; National Science and Technol-ogy Innovation 2030 Major Program[2021ZD0204503] ; Strategic Priority Research Program of Chinese Academy of Science[2021ZD0204500] ; International Partnership Program of Chinese Academy of Science[XDB32030208] ; Program of Beijing Municipal Science & Technology Commission[153D31KYSB20170059] ; National Natural Science Foundation of China[Z201100008420004] ; Strategic Priority Research Program of Chinese Academy of Science[32171461] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000861335400017 |
资助机构 | National Science and Technol-ogy Innovation 2030 Major Program ; Strategic Priority Research Program of Chinese Academy of Science ; International Partnership Program of Chinese Academy of Science ; Program of Beijing Municipal Science & Technology Commission ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Science |
源URL | [http://ir.ia.ac.cn/handle/173211/50343] |
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.Univ Chinese Acad Sci, Sch Future Technol, Beijing 101408, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Zejin,Sun, Guodong,Li, Guoqing,et al. STDIN: Spatio-temporal distilled interpolation for electron microscope images[J]. NEUROCOMPUTING,2022,505:188-202. |
APA | Wang, Zejin,Sun, Guodong,Li, Guoqing,Shen, Lijun,Zhang, Lina,&Han, Hua.(2022).STDIN: Spatio-temporal distilled interpolation for electron microscope images.NEUROCOMPUTING,505,188-202. |
MLA | Wang, Zejin,et al."STDIN: Spatio-temporal distilled interpolation for electron microscope images".NEUROCOMPUTING 505(2022):188-202. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。