Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377029793> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4377029793 abstract "In recent years, methods based on deep convolutional neural networks have made great progress in the field of image super-resolution reconstruction. However, mainstream approaches generally establish many network layers, leading to high computational costs and memory usage that are unsuitable for resource-limited edge devices. To alleviate this issue, a lightweight inverted residual attention network (IRAN) is proposed to obtain better super-resolution reconstruction performance with lower parameters and computation. The main structure of the IRAN consists of a series of inverted residual attention groups (IRAGs), which are mainly composed of several inverted residual attention blocks (IRABs). IRAB effectively reduces the network parameters and computation while extracting depth features by introducing the inverted residual structure and uses the simple channel attention mechanism to learn the important channel feature information. In addition, an enhanced spatial attention mechanism is introduced at the beginning and end of IRAG to further improve the reconstruction performance of the network. The experimental results show that compared with the mainstream lightweight networks, not only the peak signal-to-noise ratio and structural similarity of image quality metrics are better but also the parameters and the computational effort of the network are lower." @default.
- W4377029793 created "2023-05-19" @default.
- W4377029793 creator A5045001101 @default.
- W4377029793 creator A5052795742 @default.
- W4377029793 creator A5060390229 @default.
- W4377029793 creator A5064797445 @default.
- W4377029793 creator A5080509028 @default.
- W4377029793 date "2023-05-18" @default.
- W4377029793 modified "2023-10-17" @default.
- W4377029793 title "Lightweight image super-resolution reconstruction based on inverted residual attention network" @default.
- W4377029793 doi "https://doi.org/10.1117/1.jei.32.3.033009" @default.
- W4377029793 hasPublicationYear "2023" @default.
- W4377029793 type Work @default.
- W4377029793 citedByCount "0" @default.
- W4377029793 crossrefType "journal-article" @default.
- W4377029793 hasAuthorship W4377029793A5045001101 @default.
- W4377029793 hasAuthorship W4377029793A5052795742 @default.
- W4377029793 hasAuthorship W4377029793A5060390229 @default.
- W4377029793 hasAuthorship W4377029793A5064797445 @default.
- W4377029793 hasAuthorship W4377029793A5080509028 @default.
- W4377029793 hasConcept C11413529 @default.
- W4377029793 hasConcept C124101348 @default.
- W4377029793 hasConcept C127162648 @default.
- W4377029793 hasConcept C141379421 @default.
- W4377029793 hasConcept C153180895 @default.
- W4377029793 hasConcept C154945302 @default.
- W4377029793 hasConcept C155512373 @default.
- W4377029793 hasConcept C205372480 @default.
- W4377029793 hasConcept C31972630 @default.
- W4377029793 hasConcept C41008148 @default.
- W4377029793 hasConcept C45374587 @default.
- W4377029793 hasConcept C50644808 @default.
- W4377029793 hasConcept C76155785 @default.
- W4377029793 hasConcept C81363708 @default.
- W4377029793 hasConceptScore W4377029793C11413529 @default.
- W4377029793 hasConceptScore W4377029793C124101348 @default.
- W4377029793 hasConceptScore W4377029793C127162648 @default.
- W4377029793 hasConceptScore W4377029793C141379421 @default.
- W4377029793 hasConceptScore W4377029793C153180895 @default.
- W4377029793 hasConceptScore W4377029793C154945302 @default.
- W4377029793 hasConceptScore W4377029793C155512373 @default.
- W4377029793 hasConceptScore W4377029793C205372480 @default.
- W4377029793 hasConceptScore W4377029793C31972630 @default.
- W4377029793 hasConceptScore W4377029793C41008148 @default.
- W4377029793 hasConceptScore W4377029793C45374587 @default.
- W4377029793 hasConceptScore W4377029793C50644808 @default.
- W4377029793 hasConceptScore W4377029793C76155785 @default.
- W4377029793 hasConceptScore W4377029793C81363708 @default.
- W4377029793 hasIssue "03" @default.
- W4377029793 hasLocation W43770297931 @default.
- W4377029793 hasOpenAccess W4377029793 @default.
- W4377029793 hasPrimaryLocation W43770297931 @default.
- W4377029793 hasRelatedWork W2099840350 @default.
- W4377029793 hasRelatedWork W2175746458 @default.
- W4377029793 hasRelatedWork W2732542196 @default.
- W4377029793 hasRelatedWork W2738221750 @default.
- W4377029793 hasRelatedWork W2760085659 @default.
- W4377029793 hasRelatedWork W2767651786 @default.
- W4377029793 hasRelatedWork W2883200793 @default.
- W4377029793 hasRelatedWork W2973451922 @default.
- W4377029793 hasRelatedWork W3012978760 @default.
- W4377029793 hasRelatedWork W3093612317 @default.
- W4377029793 hasVolume "32" @default.
- W4377029793 isParatext "false" @default.
- W4377029793 isRetracted "false" @default.
- W4377029793 workType "article" @default.