Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308118670> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4308118670 endingPage "14151" @default.
- W4308118670 startingPage "14151" @default.
- W4308118670 abstract "Single image super-resolution (SISR) based on deep learning is a key research problem in the field of computer vision. However, existing super-resolution reconstruction algorithms often improve the quality of image reconstruction through a single network depth, ignoring the problems of reconstructing image texture structure and easy overfitting of network training. Therefore, this paper proposes a deep unfolding super-resolution network (USRNet) reconstruction method under the integrating channel attention mechanism, which is expected to improve the image resolution and restore the high-frequency information of the image. Thus, the image appears sharper. First, by assigning different weights to features, focusing on more important features and suppressing unimportant features, the details such as image edges and textures are better recovered, and the generalization ability is improved to cope with more complex scenes. Then, the CA (Channel Attention) module is added to USRNet, and the network depth is increased to better express high-frequency features; multi-channel mapping is introduced to extract richer features and enhance the super-resolution reconstruction effect of the model. The experimental results show that the USRNet with integrating channel attention has a faster convergence rate, is not prone to overfitting, and can be converged after 10,000 iterations; the average peak signal-to-noise ratios on the Set5 and Set12 datasets after the side length enlarged by two times are, respectively, 32.23 dB and 29.72 dB, and are dramatically improved compared with SRCNN, SRMD, PAN, and RCAN. The algorithm can generate high-resolution images with clear outlines, and the super-resolution effect is better." @default.
- W4308118670 created "2022-11-08" @default.
- W4308118670 creator A5014519784 @default.
- W4308118670 creator A5014539863 @default.
- W4308118670 creator A5022949716 @default.
- W4308118670 creator A5024066088 @default.
- W4308118670 creator A5038627151 @default.
- W4308118670 creator A5056982659 @default.
- W4308118670 date "2022-10-30" @default.
- W4308118670 modified "2023-10-14" @default.
- W4308118670 title "Deep USRNet Reconstruction Method Based on Combined Attention Mechanism" @default.
- W4308118670 cites W1885185971 @default.
- W4308118670 cites W1963623641 @default.
- W4308118670 cites W2016860730 @default.
- W4308118670 cites W2035677848 @default.
- W4308118670 cites W2117317262 @default.
- W4308118670 cites W2150081556 @default.
- W4308118670 cites W2940835550 @default.
- W4308118670 cites W3022900894 @default.
- W4308118670 cites W3033835243 @default.
- W4308118670 cites W3126069796 @default.
- W4308118670 cites W3195459588 @default.
- W4308118670 cites W4226069575 @default.
- W4308118670 doi "https://doi.org/10.3390/su142114151" @default.
- W4308118670 hasPublicationYear "2022" @default.
- W4308118670 type Work @default.
- W4308118670 citedByCount "1" @default.
- W4308118670 countsByYear W43081186702023 @default.
- W4308118670 crossrefType "journal-article" @default.
- W4308118670 hasAuthorship W4308118670A5014519784 @default.
- W4308118670 hasAuthorship W4308118670A5014539863 @default.
- W4308118670 hasAuthorship W4308118670A5022949716 @default.
- W4308118670 hasAuthorship W4308118670A5024066088 @default.
- W4308118670 hasAuthorship W4308118670A5038627151 @default.
- W4308118670 hasAuthorship W4308118670A5056982659 @default.
- W4308118670 hasBestOaLocation W43081186701 @default.
- W4308118670 hasConcept C108583219 @default.
- W4308118670 hasConcept C11413529 @default.
- W4308118670 hasConcept C115961682 @default.
- W4308118670 hasConcept C127162648 @default.
- W4308118670 hasConcept C134306372 @default.
- W4308118670 hasConcept C141379421 @default.
- W4308118670 hasConcept C153180895 @default.
- W4308118670 hasConcept C154945302 @default.
- W4308118670 hasConcept C177148314 @default.
- W4308118670 hasConcept C22019652 @default.
- W4308118670 hasConcept C26517878 @default.
- W4308118670 hasConcept C31972630 @default.
- W4308118670 hasConcept C33923547 @default.
- W4308118670 hasConcept C38652104 @default.
- W4308118670 hasConcept C41008148 @default.
- W4308118670 hasConcept C50644808 @default.
- W4308118670 hasConcept C76155785 @default.
- W4308118670 hasConceptScore W4308118670C108583219 @default.
- W4308118670 hasConceptScore W4308118670C11413529 @default.
- W4308118670 hasConceptScore W4308118670C115961682 @default.
- W4308118670 hasConceptScore W4308118670C127162648 @default.
- W4308118670 hasConceptScore W4308118670C134306372 @default.
- W4308118670 hasConceptScore W4308118670C141379421 @default.
- W4308118670 hasConceptScore W4308118670C153180895 @default.
- W4308118670 hasConceptScore W4308118670C154945302 @default.
- W4308118670 hasConceptScore W4308118670C177148314 @default.
- W4308118670 hasConceptScore W4308118670C22019652 @default.
- W4308118670 hasConceptScore W4308118670C26517878 @default.
- W4308118670 hasConceptScore W4308118670C31972630 @default.
- W4308118670 hasConceptScore W4308118670C33923547 @default.
- W4308118670 hasConceptScore W4308118670C38652104 @default.
- W4308118670 hasConceptScore W4308118670C41008148 @default.
- W4308118670 hasConceptScore W4308118670C50644808 @default.
- W4308118670 hasConceptScore W4308118670C76155785 @default.
- W4308118670 hasIssue "21" @default.
- W4308118670 hasLocation W43081186701 @default.
- W4308118670 hasOpenAccess W4308118670 @default.
- W4308118670 hasPrimaryLocation W43081186701 @default.
- W4308118670 hasRelatedWork W2742991909 @default.
- W4308118670 hasRelatedWork W2767651786 @default.
- W4308118670 hasRelatedWork W2954086440 @default.
- W4308118670 hasRelatedWork W3035162004 @default.
- W4308118670 hasRelatedWork W3099765033 @default.
- W4308118670 hasRelatedWork W3208327626 @default.
- W4308118670 hasRelatedWork W4220996320 @default.
- W4308118670 hasRelatedWork W4283701629 @default.
- W4308118670 hasRelatedWork W4285802257 @default.
- W4308118670 hasRelatedWork W4362499066 @default.
- W4308118670 hasVolume "14" @default.
- W4308118670 isParatext "false" @default.
- W4308118670 isRetracted "false" @default.
- W4308118670 workType "article" @default.