The Swin Transformer image super-resolution reconstruction network only
relies on the long-range relationship of window attention and shifted window
attention to explore features. This mechanism has two limitations. On the one
hand, it only focuses on global features while ignoring local features. On the
other hand, it is only concerned with spatial feature interactions while
ignoring channel features and channel interactions, thus limiting its
non-linear mapping ability. To address the above limitations, this paper
proposes enhanced Swin Transformer modules via alternating aggregation of
local-global features. In the local feature aggregation stage, this paper
introduces shift convolution to realize the interaction between local spatial
information and channel information. This paper proposes a block sparse global
perception module in the global feature aggregation stage. This module
organizes the spatial information first, then sends the recombination
information into a spatial gating unit to implement the further interaction of
spatial and channel information. Then, a multi-scale self-attention module and
a low-parameter residual channel attention module are introduced to realize
information aggregation at different scales. Finally, the proposed network is
validated on five publicly available datasets. The experimental results show
that the proposed network outperforms the other state-of-the-art
super-resolution networks.

本论文通过交替聚合局部全局特征，引入了位移卷积实现局部空间信息和通道信息的交互，并提出了块稀疏全局感知模块以进一步实现空间和通道信息的交互。同时，引入了多尺度自注意模块和低参数残差通道注意模块，实现了不同尺度上的信息聚合。在五个公开数据集上验证了提出的网络，在超分辨率方面超过了其他最先进的网络。

基于增强的 Swin Transformer 及本地 - 全局特征的交替聚合的图像超分辨重建网络

Image Super-resolution Reconstruction Network based on Enhanced Swin  Transformer via Alternating Aggregation of Local-Global Features

Recently, transformer-based methods have demonstrated impressive results in
various vision tasks, including image super-resolution (SR), by exploiting the
self-attention (SA) for feature extraction. However, the computation of SA in
most existing transformer based models is very expensive, while some employed
operations may be redundant for the SR task. This limits the range of SA
computation and consequently the SR performance. In this work, we propose an
efficient long-range attention network (ELAN) for image SR. Specifically, we
first employ shift convolution (shift-conv) to effectively extract the image
local structural information while maintaining the same level of complexity as
1x1 convolution, then propose a group-wise multi-scale self-attention (GMSA)
module, which calculates SA on non-overlapped groups of features using
different window sizes to exploit the long-range image dependency. A highly
efficient long-range attention block (ELAB) is then built by simply cascading
two shift-conv with a GMSA module, which is further accelerated by using a
shared attention mechanism. Without bells and whistles, our ELAN follows a
fairly simple design by sequentially cascading the ELABs. Extensive experiments
demonstrate that ELAN obtains even better results against the transformer-based
SR models but with significantly less complexity. The source code can be found
at this https URL

该论文提出了一种高效的长程注意力网络，使用变换器和转移学习结构可用于图像超分辨率，其中包括自我注意力机制、移位卷积和多尺度自我注意力模块。