Efficient Mixed Transformer for Single Image Super-Resolution
This work addresses efficiency and locality issues in super-resolution for image processing applications, representing an incremental improvement over existing Transformer methods.
The paper tackles the limitations of Transformer-based methods in single image super-resolution, such as lack of locality and high complexity, by proposing an Efficient Mixed Transformer (EMT) that uses a Mixed Transformer Block with Pixel Mixer and striped window self-attention, achieving state-of-the-art performance on benchmark datasets.
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 in the field of super-resolution (SR). 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 shifting operations. At the same time, no additional complexity is introduced as PM has no parameters and floating-point operations. Moreover, we employ striped window for SA (SWSA) to gain an efficient global dependency modelling by utilizing image anisotropy. Experimental results show that EMT outperforms the existing methods on benchmark dataset and achieved state-of-the-art performance. The Code is available at https://github.com/Fried-Rice-Lab/FriedRiceLab.