Efficient mixed transformer for single image super-resolution
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE(2024)
摘要
Recently, transformer -based methods have achieved impressive results in single image super -resolution (SISR). However, the lack of locality mechanism and high complexity limit their application. To solve these problems, we propose a new method, Efficient Mixed Transformer (EMT), in this study. Specifically, we propose the Mixed Transformer Block (MTB), consisting of multiple consecutive transformer layers, in some of which the Pixel Mixer (PM) is used to replace the Self -Attention (SA). PM can enhance the local knowledge aggregation with pixel mismatch operations, and no additional complexity is introduced as PM has no parameters and floating-point operations. Moreover, we develop striped window SA to gain an efficient global dependency modeling by utilizing image anisotropy. Experimental results show that EMT outperforms the existing methods on benchmark dataset and achieved state-of-the-art performance.
更多查看译文
关键词
Super-resolution,Long-range attention,Transformer,Locality
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要