TY - GEN
T1 - Lightweight non-local network for image super-resolution
AU - Wang, Risheng
AU - Lei, Tao
AU - Zhou, Wenzheng
AU - Wang, Qi
AU - Meng, Hongying
AU - Nandi, Asoke K.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - The popular deep convolutional networks used for image super-resolution (SR) reconstruction often increase the network depth and employ attention mechanism to improve image reconstruction effect. However, these networks suffer from two problems. The first is the deeper network easily causes higher computational cost and more GPU memory usage. The second is traditional attention mechanism often misses the spatial information of images leading the loss of image detail information. To address these issues, we propose a lightweight non-local network (LNLN) for image super resolution in this paper. The proposed network makes two contributions. First, we use non-local module instead of normal attention module to obtain larger receptive field and extract more comprehensive feature information, which is helpful for improving image SR reconstruction results. Secondly, we use the depthwise separable convolution (DSC) instead of the vanilla convolution to reconstruct the residual block, which greatly reduces the number of parameters and computational cost. The proposed LNLN and comparative networks are evaluated on five commonly public datasets, and experiments demonstrate that the proposed LNLN is superior to state-of-the-art networks in terms of reconstruction performance, the number of parameters and storage space.
AB - The popular deep convolutional networks used for image super-resolution (SR) reconstruction often increase the network depth and employ attention mechanism to improve image reconstruction effect. However, these networks suffer from two problems. The first is the deeper network easily causes higher computational cost and more GPU memory usage. The second is traditional attention mechanism often misses the spatial information of images leading the loss of image detail information. To address these issues, we propose a lightweight non-local network (LNLN) for image super resolution in this paper. The proposed network makes two contributions. First, we use non-local module instead of normal attention module to obtain larger receptive field and extract more comprehensive feature information, which is helpful for improving image SR reconstruction results. Secondly, we use the depthwise separable convolution (DSC) instead of the vanilla convolution to reconstruct the residual block, which greatly reduces the number of parameters and computational cost. The proposed LNLN and comparative networks are evaluated on five commonly public datasets, and experiments demonstrate that the proposed LNLN is superior to state-of-the-art networks in terms of reconstruction performance, the number of parameters and storage space.
KW - Deep learning
KW - Depthwise separable convolution (DSC)
KW - Image super-resolution (SR)
KW - Non-local module
UR - http://www.scopus.com/inward/record.url?scp=85115054039&partnerID=8YFLogxK
U2 - 10.1109/ICASSP39728.2021.9414527
DO - 10.1109/ICASSP39728.2021.9414527
M3 - 会议稿件
AN - SCOPUS:85115054039
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1625
EP - 1629
BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Y2 - 6 June 2021 through 11 June 2021
ER -