From Local to Global: Efficient Dual Attention Mechanism for Single Image Super-Resolution

IEEE Access

Pei Zhang¹  Edmund Y. Lam¹ 

[1] Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, SAR, China;

关键词: Attention mechanism;    convolutional neural networks;    super-resolution;   

DOI  :  10.1109/ACCESS.2021.3105726

来源: DOAJ

【 摘 要 】

Convolutional neural networks (CNNs) have become a powerful approach for single image super-resolution (SISR). Recently, attention mechanisms are incorporated to enhance the network performance further. However, most methods use them locally to gather and model information at a single layer, which is not sufficient to capture the hierarchical relationship among various channels and restore high-frequency features. Here, we propose an efficient dual attention mechanism, with a global cross-layer attention (GCA) mechanism to emphasize high-frequency information learning by modeling cross-layer feature dependencies, and a local enhanced attention (LEA) mechanism, complementing GCA by offering attention-aware features for accurate feature fusion and also facilitating structure preservation. Experiments demonstrate that our method adapts well to multiple image degradation models and performs favorably against state-of-the-art methods.

【 授权许可】

Unknown