Attention in Attention Network for Image Super-Resolution

Image super-resolution (SR) is a low-level computer vision problem, which aims at recovering a high-resolution (HR) image from a low-resolution (LR) observation. In recent years, SR methods based on deep convolution neural networks (CNN) have achieved significant success, the performance of the CNN model is constantly growing. Recently, some methods begin to aggregate attention mechanism into the SR model, e.g., channel attention and spatial attention . The introduction of attention mechanism greatly improves the performance of these networks by enhancing the representation capability of static CNNs. Existing studies have shown that the attention mechanism is very important for high-performance super-division models . However, few work really discuss " why attention works and how does it work ".