Feedback Pyramid Attention Networks for Single Image Super-Resolution

Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement. However, most CNN-based methods mainly focus on feed-forward architecture design and neglect to explore the feedback mechanism, which usually exists in the human...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2023-09, Vol.33 (9), p.1-1
Main Authors: Wu, Huapeng, Gui, Jie, Zhang, Jun, Kwok, James T., Wei, Zhihui
Format: Article
Language:English
Subjects:
Artificial neural networks
Context modeling
Convolution
Convolutional neural networks
Feature extraction
Feedback
feedback mechanism
Image reconstruction
Image resolution
Laplace equations
pyramid non-local structure
Super-resolution
Superresolution
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement. However, most CNN-based methods mainly focus on feed-forward architecture design and neglect to explore the feedback mechanism, which usually exists in the human visual system. In this paper, we propose feedback pyramid attention networks (FPAN) to fully exploit the mutual dependencies of features. Specifically, a novel feedback connection structure is developed to enhance low-level feature expression with high-level information. In our method, the output of each layer in the first stage is also used as the input of the corresponding layer in the next state to re-update the previous low-level filters. Moreover, we introduce a pyramid non-local structure to model global contextual information in different scales and improve the discriminative representation of the network. Extensive experimental results on various datasets demonstrate the superiority of our FPAN in comparison with the state-of-the-art SR methods.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2023.3250657