GRFormer：面向轻量级单图像超分辨率的分组残差自注意力
GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution
AI总结：
针对Transformer类单图像超分辨率模型降参减算易致性能下降的问题，提出GRFormer，通过分组残差自注意力的两个创新组件，在大幅降低参数与计算量的同时实现了性能超越现有SOTA的效果。
摘要：
已有研究表明，降低基于Transformer的单图像超分辨率（SISR）模型（如SwinIR）的参数开销与计算量通常会导致性能下降。本文提出了一种高效轻量的方法GRFormer，该方法不仅降低了参数开销与计算量，还大幅提升了性能。GRFormer的核心是分组残差自注意力（GRSA），其专门针对两个基本组件设计。首先，它引入了一种新型分组残差层（GRL），替代自注意力中的查询、键、值（QKV）线性层，旨在高效降低参数开销、计算量的同时减少性能损失。其次，它集成了紧凑的指数空间相对位置偏置（ES-RPB），替代原始相对位置偏置，在进一步减少参数量的同时提升位置信息的表征能力。大量实验结果表明，在×2、×3和×4倍SISR任务上，GRFormer的性能优于现有最先进的基于Transformer的方法；在DIV2K数据集上训练时，其峰值信噪比（PSNR）最高比SOTA高出0.23dB，同时仅在自注意力模块中，参数量和乘加运算量（MACs）分别减少了约60%和49%。我们希望这种简单有效、可轻松应用于基于窗口划分自注意力的超分辨率模型的方法，能为图像超分辨率的后续研究提供有用的工具。代码可在https://github.com/sisrformer/GRFormer 获取。
英文摘要：
Previous works have shown that reducing parameter overhead and computations for transformer-based single image super-resolution (SISR) models (e.g., SwinIR) usually leads to a reduction of performance. In this paper, we present GRFormer, an efficient and lightweight method, which not only reduces the parameter overhead and computations, but also greatly improves performance. The core of GRFormer is Grouped Residual Self-Attention (GRSA), which is specifically oriented towards two fundamental components. Firstly, it introduces a novel grouped residual layer (GRL) to replace the Query, Key, Value (QKV) linear layer in self-attention, aimed at efficiently reducing parameter overhead, computations, and performance loss at the same time. Secondly, it integrates a compact Exponential-Space Relative Position Bias (ES-RPB) as a substitute for the original relative position bias to improve the ability to represent position information while further minimizing the parameter count. Extensive experimental results demonstrate that GRFormer outperforms state-of-the-art transformer-based methods for $\times$2, $\times$3 and $\times$4 SISR tasks, notably outperforming SOTA by a maximum PSNR of 0.23dB when trained on the DIV2K dataset, while reducing the number of parameter and MACs by about \textbf{60\%} and \textbf{49\% } in only self-attention module respectively. We hope that our simple and effective method that can easily applied to SR models based on window-division self-attention can serve as a useful tool for further research in image super-resolution. The code is available at \url{https://github.com/sisrformer/GRFormer}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
