Scholarlink

<p>Image super-resolution (SR) is a computer vision task that reconstructs high-resolution (HR) images from low-resolution (LR) images using algorithms. Current Transformer architectures typically employ modules in a sequential arrangement, which often results in the loss of significant effective features across certain layers. Additionally, the Transformer-based models extract feature information through local windows, but they are prone to losing global features. To prevent the loss of valuable features without increasing model complexity, we propose a novel model, Weighted Hierarchy Aggregation(WHA). The core of our WHA is the Hierarchy Aggregation Block (HAB), which builds upon the techniques of residual and dense connections by introducing a learned weighting mechanism that adaptively emphasizes the most valuable features from each layer in the final output. Furthermore, to address the issue that local window self-attention tends to lose global features, we propose a Global Residual Self-Attention Block(GRSAB). The GRSAB can effectively solve the problem of global information loss by introducing two-dimensional channel attention. Our WHA not only accelerates network training but also effectively captures both local and global features, significantly enhancing super-resolution performance. Through extensive comparative experiments and ablation studies, our results demonstrate the high efficiency of HAB, especially in lightweight SR tasks. In the <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation>4 super-resolution task, our model achieves a 26.88dB PSNR score on the Urban100 benchmark dataset, demonstrating its efficacy through comparative analysis with other models sharing similar architectural frameworks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

WHANet: Weighted Hierarchical Attention for Lightweight SR

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月22日

查看全文
  • Man Tang,
  • Shen Wu,
  • Yilin He,
  • Wenlin Yu,
  • Yuyao Lin,
  • Congcong Ma

摘要

Image super-resolution (SR) is a computer vision task that reconstructs high-resolution (HR) images from low-resolution (LR) images using algorithms. Current Transformer architectures typically employ modules in a sequential arrangement, which often results in the loss of significant effective features across certain layers. Additionally, the Transformer-based models extract feature information through local windows, but they are prone to losing global features. To prevent the loss of valuable features without increasing model complexity, we propose a novel model, Weighted Hierarchy Aggregation(WHA). The core of our WHA is the Hierarchy Aggregation Block (HAB), which builds upon the techniques of residual and dense connections by introducing a learned weighting mechanism that adaptively emphasizes the most valuable features from each layer in the final output. Furthermore, to address the issue that local window self-attention tends to lose global features, we propose a Global Residual Self-Attention Block(GRSAB). The GRSAB can effectively solve the problem of global information loss by introducing two-dimensional channel attention. Our WHA not only accelerates network training but also effectively captures both local and global features, significantly enhancing super-resolution performance. Through extensive comparative experiments and ablation studies, our results demonstrate the high efficiency of HAB, especially in lightweight SR tasks. In the \(\times\) 4 super-resolution task, our model achieves a 26.88dB PSNR score on the Urban100 benchmark dataset, demonstrating its efficacy through comparative analysis with other models sharing similar architectural frameworks.