文献类型：期刊文献

英文题名：Multi-Attention Residual Network for Image Super Resolution

作者：Chang, Qing[1];Jia, Xiaotian[1];Lu, Chenhao[1];Ye, Jian[1]

机构：[1]East China Univ Sci & Technol, Coll Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：36

期号：08

外文期刊名：INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE

收录：;EI(收录号：20222812355278);WOS:【SCI-EXPANDED(收录号:WOS:000821707100013)】；

基金：This work was supported by the National Natural Science Foundation of China (No. 61976091).

语种：英文

外文关键词：Super resolution; deep convolutional neural network; multi-attention residual network; global hierarchical feature fusion

摘要：Recently, many studies have shown that deep convolutional neural network can achieve superior performance in image super resolution (SR). The majority of current CNN-based SR methods tend to use deeper architecture to get excellent performance. However, with the growing depth and width of network, the hierarchical features from low-resolution (LR) images cannot be exploited effectively. On the other hand, most models lack the ability of discriminating different types of information and treating them equally, which results in limiting the representational capacity of the models. In this study, we propose the multi-attention residual network (MARN) to address these problems. Specifically, we propose a new multi-attention residual block (MARB), which is composed of attention mechanism and multi-scale residual network. At the beginning of each residual block, the channel importance of image features is adaptively recalibrated by attention mechanism. Then, we utilize convolutional kernels of different sizes to adaptively extract the multi-attention features on different scales. At the end of blocks, local multi-attention features fusion is applied to get more effective hierarchical features. After obtaining the outputs of each MARB, global hierarchical feature fusion jointly fuses all hierarchical features for reconstructing images. Our extensive experiments show that our model outperforms most of the state-of-the-art methods.