Learning From Errors in Super-Resolution | |
Tang, Yi1; Yuan, Yuan2 | |
作者部门 | 光学影像学习与分析中心 |
2014-11-01 | |
发表期刊 | IEEE TRANSACTIONS ON CYBERNETICS |
ISSN | 2168-2267 |
卷号 | 44期号:11页码:2143-2154 |
摘要 | A novel framework of learning-based super-resolution is proposed by employing the process of learning from the estimation errors. The estimation errors generated by different learning-based super-resolution algorithms are statistically shown to be sparse and uncertain. The sparsity of the estimation errors means most of estimation errors are small enough. The uncertainty of the estimation errors means the location of the pixel with larger estimation error is random. Noticing the prior information about the estimation errors, a nonlinear boosting process of learning from these estimation errors is introduced into the general framework of the learning-based super-resolution. Within the novel framework of super-resolution, a low-rank decomposition technique is used to share the information of different super-resolution estimations and to remove the sparse estimation errors from different learning algorithms or training samples. The experimental results show the effectiveness and the efficiency of the proposed framework in enhancing the performance of different learning-based algorithms. |
文章类型 | Article |
关键词 | Boosting Learning-based Super-resolution Low-rank Decomposition Sparsity |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TCYB.2014.2301732 |
收录类别 | SCI ; EI |
关键词[WOS] | SINGLE-IMAGE SUPERRESOLUTION ; SUPER RESOLUTION ; DICTIONARY ; REGRESSION ; STABILITY |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Cybernetics |
WOS记录号 | WOS:000343319700014 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/22372 |
专题 | 光谱成像技术研究室 |
作者单位 | 1.Yunnan Univ Nationalities, Sch Math & Comp Sci, Kunming 650500, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Tang, Yi,Yuan, Yuan. Learning From Errors in Super-Resolution[J]. IEEE TRANSACTIONS ON CYBERNETICS,2014,44(11):2143-2154. |
APA | Tang, Yi,&Yuan, Yuan.(2014).Learning From Errors in Super-Resolution.IEEE TRANSACTIONS ON CYBERNETICS,44(11),2143-2154. |
MLA | Tang, Yi,et al."Learning From Errors in Super-Resolution".IEEE TRANSACTIONS ON CYBERNETICS 44.11(2014):2143-2154. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Learning From Errors(33824KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY | 请求全文 |
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 |
[Tang, Yi]的文章 |
[Yuan, Yuan]的文章 |
百度学术 |
百度学术中相似的文章 |
[Tang, Yi]的文章 |
[Yuan, Yuan]的文章 |
必应学术 |
必应学术中相似的文章 |
[Tang, Yi]的文章 |
[Yuan, Yuan]的文章 |
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