ODE-inspired Network Design for Single Image Super-Resolution
文献类型:会议论文
作者 | He, Xiangyu2; Mo, Zitao2; Wang, Peisong2; Liu, Yang1; Yang, Mingyuan1; Cheng, Jian2 |
出版日期 | 2019-06 |
会议日期 | June 16th - June 20th |
会议地点 | Long Beach, CA |
页码 | 1732–1741 |
英文摘要 | Single image super-resolution, as a high dimensional structured prediction problem, aims to characterize fine-grain information given a low-resolution sample. Recent advances in convolutional neural networks are introduced into super-resolution and push forward progress in this field. Current studies have achieved impressive performance by manually designing deep residual neural networks but overly relies on practical experience. In this paper, we propose to adopt an ordinary differential equation (ODE)-inspired design scheme for single image super-resolution, which have brought us a new understanding of ResNet in classification problems. Not only is it interpretable for super-resolution but it provides a reliable guideline on network designs. By casting the numerical schemes in ODE as blueprints, we derive two types of network structures: LF-block and RK-block, which correspond to the Leapfrog method and Runge-Kutta method in numerical ordinary differential equations. We evaluate our models on benchmark datasets, and the results show that our methods surpass the state-of-the-arts while keeping comparable parameters and operations. |
产权排序 | 1 |
会议录出版者 | IEEE |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/40124] |
专题 | 类脑芯片与系统研究 |
作者单位 | 1.Alibaba Group 2.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | He, Xiangyu,Mo, Zitao,Wang, Peisong,et al. ODE-inspired Network Design for Single Image Super-Resolution[C]. 见:. Long Beach, CA. June 16th - June 20th. |
入库方式: OAI收割
来源:自动化研究所
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。