Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289755907> ?p ?o ?g. }
- W4289755907 abstract "In recent years, various convolutional neural networks have successfully applied to single-image super-resolution task. However, most existing models with deeper or wider networks require heavy computation and memory consumption that restrict them in practice. To solve the above questions, we propose a lightweight multiscale residual attention network, which not merely can extract more detail to improve the quality of the image but also decrease the usage of the parameters. More specifically, a multiscale residual attention block (MRAB) as the basic unit can fully exploit the image features with different sizes of convolutional kernels. Meanwhile, the attention mechanism can be adaptive to recalibrate channel and spatial information of feature mappings. Furthermore, a local information integration module (LFIM) is designed as the network architecture to maximize the use of local information. The LFIM consists of several MRAB and a local skip connection to complement information loss. Our experimental results show that our method is superior to the representative algorithms in performance with fewer parameters and computational overhead. Code is available at https://github.com/xiaotian3/EMRAB." @default.
- W4289755907 created "2022-08-04" @default.
- W4289755907 creator A5045117407 @default.
- W4289755907 creator A5047732836 @default.
- W4289755907 creator A5053766820 @default.
- W4289755907 creator A5060499714 @default.
- W4289755907 creator A5079493144 @default.
- W4289755907 date "2022-07-01" @default.
- W4289755907 modified "2023-09-27" @default.
- W4289755907 title "Lightweight image super-resolution with multiscale residual attention network" @default.
- W4289755907 cites W1580389772 @default.
- W4289755907 cites W1791560514 @default.
- W4289755907 cites W1885185971 @default.
- W4289755907 cites W1930824406 @default.
- W4289755907 cites W1992408872 @default.
- W4289755907 cites W2047920195 @default.
- W4289755907 cites W2097117768 @default.
- W4289755907 cites W2118963448 @default.
- W4289755907 cites W2121058967 @default.
- W4289755907 cites W2121927366 @default.
- W4289755907 cites W2133665775 @default.
- W4289755907 cites W2142884912 @default.
- W4289755907 cites W2144468361 @default.
- W4289755907 cites W2149669120 @default.
- W4289755907 cites W2150081556 @default.
- W4289755907 cites W2157190232 @default.
- W4289755907 cites W2192954843 @default.
- W4289755907 cites W2214802144 @default.
- W4289755907 cites W2242218935 @default.
- W4289755907 cites W2476548250 @default.
- W4289755907 cites W2503339013 @default.
- W4289755907 cites W2561139386 @default.
- W4289755907 cites W2607041014 @default.
- W4289755907 cites W2740139074 @default.
- W4289755907 cites W2741137940 @default.
- W4289755907 cites W2747898905 @default.
- W4289755907 cites W2866634454 @default.
- W4289755907 cites W2884585870 @default.
- W4289755907 cites W2895598217 @default.
- W4289755907 cites W2928165649 @default.
- W4289755907 cites W2963372104 @default.
- W4289755907 cites W2963420686 @default.
- W4289755907 cites W2963495494 @default.
- W4289755907 cites W2963645458 @default.
- W4289755907 cites W2964125708 @default.
- W4289755907 cites W3018586778 @default.
- W4289755907 cites W3034247386 @default.
- W4289755907 cites W3036694380 @default.
- W4289755907 cites W3096739052 @default.
- W4289755907 cites W3107716502 @default.
- W4289755907 cites W3143657944 @default.
- W4289755907 cites W3163767593 @default.
- W4289755907 cites W3170026688 @default.
- W4289755907 cites W3182950293 @default.
- W4289755907 cites W4200392605 @default.
- W4289755907 cites W7682646 @default.
- W4289755907 doi "https://doi.org/10.1117/1.jei.31.4.043028" @default.
- W4289755907 hasPublicationYear "2022" @default.
- W4289755907 type Work @default.
- W4289755907 citedByCount "0" @default.
- W4289755907 crossrefType "journal-article" @default.
- W4289755907 hasAuthorship W4289755907A5045117407 @default.
- W4289755907 hasAuthorship W4289755907A5047732836 @default.
- W4289755907 hasAuthorship W4289755907A5053766820 @default.
- W4289755907 hasAuthorship W4289755907A5060499714 @default.
- W4289755907 hasAuthorship W4289755907A5079493144 @default.
- W4289755907 hasConcept C111919701 @default.
- W4289755907 hasConcept C113775141 @default.
- W4289755907 hasConcept C11413529 @default.
- W4289755907 hasConcept C115961682 @default.
- W4289755907 hasConcept C124101348 @default.
- W4289755907 hasConcept C126780896 @default.
- W4289755907 hasConcept C138885662 @default.
- W4289755907 hasConcept C153180895 @default.
- W4289755907 hasConcept C154945302 @default.
- W4289755907 hasConcept C155512373 @default.
- W4289755907 hasConcept C165696696 @default.
- W4289755907 hasConcept C177264268 @default.
- W4289755907 hasConcept C194257627 @default.
- W4289755907 hasConcept C199360897 @default.
- W4289755907 hasConcept C205372480 @default.
- W4289755907 hasConcept C2524010 @default.
- W4289755907 hasConcept C2776257435 @default.
- W4289755907 hasConcept C2776401178 @default.
- W4289755907 hasConcept C2776760102 @default.
- W4289755907 hasConcept C2777210771 @default.
- W4289755907 hasConcept C2779960059 @default.
- W4289755907 hasConcept C31258907 @default.
- W4289755907 hasConcept C33923547 @default.
- W4289755907 hasConcept C38652104 @default.
- W4289755907 hasConcept C41008148 @default.
- W4289755907 hasConcept C41895202 @default.
- W4289755907 hasConcept C45374587 @default.
- W4289755907 hasConcept C55020928 @default.
- W4289755907 hasConcept C81363708 @default.
- W4289755907 hasConceptScore W4289755907C111919701 @default.
- W4289755907 hasConceptScore W4289755907C113775141 @default.
- W4289755907 hasConceptScore W4289755907C11413529 @default.
- W4289755907 hasConceptScore W4289755907C115961682 @default.
- W4289755907 hasConceptScore W4289755907C124101348 @default.