FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387675655> ?p ?o ?g. }

• W4387675655 abstract "In recent years, many image denoising methods have been proposed based on convolutional neural networks (CNNs). While these methods have shown continuous performance improvement by introducing various mechanisms and structures, their computational cost tends to become increasingly expensive, owing to the resulting complex network architectures. This paper aims at winning the trade-off between computational efficiency and denoising performance for CNN-based image denoisers. Towards this end, we draw inspirations from traditional variational models with wavelet analysis operators for CNN architecture design. A model-inspired CNN is proposed with four key modules: iterative encoding-decoding units inspired by the iterative denoising process, directional convolutions inspired by the separable wavelet filters, inception modules inspired by the multi-scale analysis of wavelets, and stage-wise connections inspired by the adding noise back operation. In experiments, our CNN shows high computational efficiency in both training and test, with competitive results to state-of-the-art approaches." @default.
• W4387675655 created "2023-10-17" @default.
• W4387675655 creator A5010277066 @default.
• W4387675655 creator A5037627177 @default.
• W4387675655 creator A5038130835 @default.
• W4387675655 creator A5038395547 @default.
• W4387675655 creator A5065318001 @default.
• W4387675655 creator A5085960965 @default.
• W4387675655 date "2023-10-01" @default.
• W4387675655 modified "2023-10-18" @default.
• W4387675655 title "Wavelet Analysis Model Inspired Convolutional Neural Networks for Image Denoising" @default.
• W4387675655 cites W1906770428 @default.
• W4387675655 cites W1989619792 @default.
• W4387675655 cites W1996726072 @default.
• W4387675655 cites W1999829977 @default.
• W4387675655 cites W2008357395 @default.
• W4387675655 cites W2009548700 @default.
• W4387675655 cites W2037642501 @default.
• W4387675655 cites W2048695508 @default.
• W4387675655 cites W2056370875 @default.
• W4387675655 cites W2069441534 @default.
• W4387675655 cites W2130975789 @default.
• W4387675655 cites W2142224912 @default.
• W4387675655 cites W2153663612 @default.
• W4387675655 cites W2154996879 @default.
• W4387675655 cites W2172275395 @default.
• W4387675655 cites W2205608177 @default.
• W4387675655 cites W2415447328 @default.
• W4387675655 cites W2508457857 @default.
• W4387675655 cites W2573726823 @default.
• W4387675655 cites W2613955579 @default.
• W4387675655 cites W2626739722 @default.
• W4387675655 cites W2766341514 @default.
• W4387675655 cites W2780930362 @default.
• W4387675655 cites W2801252031 @default.
• W4387675655 cites W2884283253 @default.
• W4387675655 cites W2901182545 @default.
• W4387675655 cites W2909350396 @default.
• W4387675655 cites W2963111219 @default.
• W4387675655 cites W2964046397 @default.
• W4387675655 cites W2964101377 @default.
• W4387675655 cites W2964125708 @default.
• W4387675655 cites W2967502735 @default.
• W4387675655 cites W2967641264 @default.
• W4387675655 cites W2989446488 @default.
• W4387675655 cites W3011455439 @default.
• W4387675655 cites W3021986761 @default.
• W4387675655 cites W3080848135 @default.
• W4387675655 cites W3087110941 @default.
• W4387675655 cites W3104725225 @default.
• W4387675655 cites W3114679828 @default.
• W4387675655 cites W3123837026 @default.
• W4387675655 cites W3167568784 @default.
• W4387675655 cites W3199716252 @default.
• W4387675655 cites W4225311243 @default.
• W4387675655 cites W4296551003 @default.
• W4387675655 cites W4298111778 @default.
• W4387675655 doi "https://doi.org/10.1016/j.apm.2023.10.023" @default.
• W4387675655 hasPublicationYear "2023" @default.
• W4387675655 type Work @default.
• W4387675655 citedByCount "0" @default.
• W4387675655 crossrefType "journal-article" @default.
• W4387675655 hasAuthorship W4387675655A5010277066 @default.
• W4387675655 hasAuthorship W4387675655A5037627177 @default.
• W4387675655 hasAuthorship W4387675655A5038130835 @default.
• W4387675655 hasAuthorship W4387675655A5038395547 @default.
• W4387675655 hasAuthorship W4387675655A5065318001 @default.
• W4387675655 hasAuthorship W4387675655A5085960965 @default.
• W4387675655 hasConcept C111919701 @default.
• W4387675655 hasConcept C11413529 @default.
• W4387675655 hasConcept C115903868 @default.
• W4387675655 hasConcept C115961682 @default.
• W4387675655 hasConcept C143587482 @default.
• W4387675655 hasConcept C153180895 @default.
• W4387675655 hasConcept C154945302 @default.
• W4387675655 hasConcept C163294075 @default.
• W4387675655 hasConcept C196216189 @default.
• W4387675655 hasConcept C41008148 @default.
• W4387675655 hasConcept C47432892 @default.
• W4387675655 hasConcept C57273362 @default.
• W4387675655 hasConcept C81363708 @default.
• W4387675655 hasConcept C98045186 @default.
• W4387675655 hasConcept C99498987 @default.
• W4387675655 hasConceptScore W4387675655C111919701 @default.
• W4387675655 hasConceptScore W4387675655C11413529 @default.
• W4387675655 hasConceptScore W4387675655C115903868 @default.
• W4387675655 hasConceptScore W4387675655C115961682 @default.
• W4387675655 hasConceptScore W4387675655C143587482 @default.
• W4387675655 hasConceptScore W4387675655C153180895 @default.
• W4387675655 hasConceptScore W4387675655C154945302 @default.
• W4387675655 hasConceptScore W4387675655C163294075 @default.
• W4387675655 hasConceptScore W4387675655C196216189 @default.
• W4387675655 hasConceptScore W4387675655C41008148 @default.
• W4387675655 hasConceptScore W4387675655C47432892 @default.
• W4387675655 hasConceptScore W4387675655C57273362 @default.
• W4387675655 hasConceptScore W4387675655C81363708 @default.
• W4387675655 hasConceptScore W4387675655C98045186 @default.
• W4387675655 hasConceptScore W4387675655C99498987 @default.
• W4387675655 hasLocation W43876756551 @default.
• W4387675655 hasOpenAccess W4387675655 @default.

• next