Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network | |
Long Sun; Zhenbing Liu; Xiyan Sun; Licheng Liu; Rushi Lan; Xiaonan Luo | |
刊名 | IEEE/CAA Journal of Automatica Sinica |
2021 | |
卷号 | 8期号:7页码:1271-1280 |
关键词 | Convolutional neural network (CNN) lightweight framework multi-scale super-resolution |
ISSN号 | 2329-9266 |
DOI | 10.1109/JAS.2021.1004009 |
英文摘要 | The tradeoff between efficiency and model size of the convolutional neural network (CNN) is an essential issue for applications of CNN-based algorithms to diverse real-world tasks. Although deep learning-based methods have achieved significant improvements in image super-resolution (SR), current CNN-based techniques mainly contain massive parameters and a high computational complexity, limiting their practical applications. In this paper, we present a fast and lightweight framework, named weighted multi-scale residual network (WMRN), for a better tradeoff between SR performance and computational efficiency. With the modified residual structure, depthwise separable convolutions (DS Convs) are employed to improve convolutional operations’ efficiency. Furthermore, several weighted multi-scale residual blocks (WMRBs) are stacked to enhance the multi-scale representation capability. In the reconstruction subnetwork, a group of Conv layers are introduced to filter feature maps to reconstruct the final high-quality image. Extensive experiments were conducted to evaluate the proposed model, and the comparative results with several state-of-the-art algorithms demonstrate the effectiveness of WMRN. |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44581] |
专题 | 自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica |
推荐引用方式 GB/T 7714 | Long Sun,Zhenbing Liu,Xiyan Sun,et al. Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network[J]. IEEE/CAA Journal of Automatica Sinica,2021,8(7):1271-1280. |
APA | Long Sun,Zhenbing Liu,Xiyan Sun,Licheng Liu,Rushi Lan,&Xiaonan Luo.(2021).Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network.IEEE/CAA Journal of Automatica Sinica,8(7),1271-1280. |
MLA | Long Sun,et al."Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network".IEEE/CAA Journal of Automatica Sinica 8.7(2021):1271-1280. |
个性服务 |
查看访问统计 |
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