Lightweight Image Super-Resolution via Dual Feature Aggregation Network | |
Shang Li1,2; Guixuan Zhang1; Zhengxiong Luo1,2; Jie Liu1; Zhi Zeng1; Shuwu Zhang1 | |
2021-11 | |
会议名称 | the 2st International Conference on Culture-oriented Science & Technology (ICCST) |
会议日期 | November 18-21, 2021 |
会议地点 | Beijing, China |
会议举办国 | 中国 |
会议录编者/会议主办者 | 中国科学院自动化研究所,中国传媒大学 |
产权排序 | 1 |
摘要 | With the power of deep learning, super-resolution (SR) methods enjoy a dramatic boost of performance. However, they usually have a large model size and high computational complexity, which hinders the application in devices with limited memory and computing power. Some lightweight SR methods solve this issue by directly designing shallower architectures, but it will affect SR performance. In this paper, we propose the dual feature aggregation strategy (DFA). It enhances the feature utilization via feature reuse, which largely improves the representation ability while only introducing marginal computational cost. Thus, a smaller model could achieve better cost-effectiveness with DFA. Specifically, DFA consists of local and global feature aggregation modules (LAM and GAM). They work together to further fuse hierarchical features adaptively along the channel and spatial dimensions. Extensive experiments suggest that the proposed network performs favorably against the state-of-the-art SR methods in terms of visual quality, memory footprint, and computational complexity. |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47513 |
专题 | 数字内容技术与服务研究中心_版权智能与文化计算 |
通讯作者 | Shang Li |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
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 | Shang Li,Guixuan Zhang,Zhengxiong Luo,et al. Lightweight Image Super-Resolution via Dual Feature Aggregation Network[C]//中国科学院自动化研究所,中国传媒大学,2021. |
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 | ||
ICCST-2021-Lightweig(1109KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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