FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042206181> ?p ?o ?g. }

• W3042206181 abstract "Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high computational cost and more memory storage for training a SR model, which limits their applications to SR with resource-constrained devices in real world. To resolve these problems, we propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB). Specifically, the IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. To remove redundant information obtained, a heterogeneous architecture is adopted in the IEEB. After that, the RB converts low-frequency features into high-frequency features by fusing global and local features, which is complementary with the IEEB in tackling the long-term dependency problem. Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image. The proposed LESRCNN can obtain a high-quality image by a model for different scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation. The code of LESRCNN is accessible on https://github.com/hellloxiaotian/LESRCNN." @default.
• W3042206181 created "2020-07-16" @default.
• W3042206181 creator A5010248697 @default.
• W3042206181 creator A5018318136 @default.
• W3042206181 creator A5026662451 @default.
• W3042206181 creator A5047421795 @default.
• W3042206181 creator A5063253432 @default.
• W3042206181 creator A5075541045 @default.
• W3042206181 creator A5077247900 @default.
• W3042206181 date "2020-07-08" @default.
• W3042206181 modified "2023-09-24" @default.
• W3042206181 title "Lightweight image super-resolution with enhanced CNN" @default.
• W3042206181 cites W1821462560 @default.
• W3042206181 cites W1885185971 @default.
• W3042206181 cites W1906770428 @default.
• W3042206181 cites W1919542679 @default.
• W3042206181 cites W1930824406 @default.
• W3042206181 cites W1949096787 @default.
• W3042206181 cites W1950594372 @default.
• W3042206181 cites W1992408872 @default.
• W3042206181 cites W2047920195 @default.
• W3042206181 cites W2064076387 @default.
• W3042206181 cites W2080918425 @default.
• W3042206181 cites W2121058967 @default.
• W3042206181 cites W2121927366 @default.
• W3042206181 cites W2139639076 @default.
• W3042206181 cites W2163605009 @default.
• W3042206181 cites W2194775991 @default.
• W3042206181 cites W2207282238 @default.
• W3042206181 cites W2214802144 @default.
• W3042206181 cites W2242218935 @default.
• W3042206181 cites W2476548250 @default.
• W3042206181 cites W2503339013 @default.
• W3042206181 cites W2508457857 @default.
• W3042206181 cites W2594779502 @default.
• W3042206181 cites W2607041014 @default.
• W3042206181 cites W2741137940 @default.
• W3042206181 cites W2747675701 @default.
• W3042206181 cites W2747898905 @default.
• W3042206181 cites W2795024892 @default.
• W3042206181 cites W2866634454 @default.
• W3042206181 cites W2887695188 @default.
• W3042206181 cites W2890276476 @default.
• W3042206181 cites W2893039345 @default.
• W3042206181 cites W2898136110 @default.
• W3042206181 cites W2901534369 @default.
• W3042206181 cites W2935842779 @default.
• W3042206181 cites W2944471189 @default.
• W3042206181 cites W2963182372 @default.
• W3042206181 cites W2963315679 @default.
• W3042206181 cites W2963494934 @default.
• W3042206181 cites W2963645458 @default.
• W3042206181 cites W2963774720 @default.
• W3042206181 cites W2963986095 @default.
• W3042206181 cites W2964046669 @default.
• W3042206181 cites W2964077901 @default.
• W3042206181 cites W2964101377 @default.
• W3042206181 cites W2964116203 @default.
• W3042206181 cites W2964125708 @default.
• W3042206181 cites W2964277374 @default.
• W3042206181 cites W2970140064 @default.
• W3042206181 cites W2971719842 @default.
• W3042206181 cites W2976715267 @default.
• W3042206181 cites W2982536526 @default.
• W3042206181 cites W2984957176 @default.
• W3042206181 cites W2996555576 @default.
• W3042206181 cites W2999111259 @default.
• W3042206181 cites W2999653953 @default.
• W3042206181 cites W3002332355 @default.
• W3042206181 cites W3005593316 @default.
• W3042206181 cites W3012002796 @default.
• W3042206181 cites W3026432413 @default.
• W3042206181 cites W3033835243 @default.
• W3042206181 cites W3041538488 @default.
• W3042206181 cites W3047011367 @default.
• W3042206181 cites W3100166939 @default.
• W3042206181 cites W3104468713 @default.
• W3042206181 cites W7682646 @default.
• W3042206181 doi "https://doi.org/10.48550/arxiv.2007.04344" @default.
• W3042206181 hasPublicationYear "2020" @default.
• W3042206181 type Work @default.
• W3042206181 sameAs 3042206181 @default.
• W3042206181 citedByCount "0" @default.
• W3042206181 crossrefType "posted-content" @default.
• W3042206181 hasAuthorship W3042206181A5010248697 @default.
• W3042206181 hasAuthorship W3042206181A5018318136 @default.
• W3042206181 hasAuthorship W3042206181A5026662451 @default.
• W3042206181 hasAuthorship W3042206181A5047421795 @default.
• W3042206181 hasAuthorship W3042206181A5063253432 @default.
• W3042206181 hasAuthorship W3042206181A5075541045 @default.
• W3042206181 hasAuthorship W3042206181A5077247900 @default.
• W3042206181 hasBestOaLocation W30422061811 @default.
• W3042206181 hasConcept C11413529 @default.
• W3042206181 hasConcept C115961682 @default.
• W3042206181 hasConcept C153180895 @default.
• W3042206181 hasConcept C154945302 @default.
• W3042206181 hasConcept C177264268 @default.
• W3042206181 hasConcept C19768560 @default.
• W3042206181 hasConcept C199360897 @default.
• W3042206181 hasConcept C2524010 @default.

• next