Matches in SemOpenAlex for { <https://semopenalex.org/work/W4253551851> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4253551851 endingPage "5418" @default.
- W4253551851 startingPage "5412" @default.
- W4253551851 abstract "In recent years, the Convolutional neural networks (CNN) has been active in various Artificial intelligence applications as well as computer vision tasks. We suggested an effective technique in this study to decrease the number of duplicates in feature maps of CNN. Proposed a novel convolution scheme Octave convolution (Octconv) to minimize the duplicates in the feature maps and boost the CNNs performance. The principle concept of this method is to separate the Convolutional filters into a higher frequency and lower frequency sections. In this report, we made an attempt for minimizing the spatial redundancy directly from output feature maps of CNN using the following 3 steps: First, divide the channels into higher and lower frequency parts depending on the information of the image using Multi-scale representation. Second, reduce the number of FLOPs from the low frequencies. Third, before sending the output to combine both the higher frequency and lower frequency information of the image. The key purpose of this abstract is to improve CNNs efficiency by reducing spatial redundancy in the feature maps of the convolution layer." @default.
- W4253551851 created "2022-05-12" @default.
- W4253551851 date "2020-03-30" @default.
- W4253551851 modified "2023-09-24" @default.
- W4253551851 title "Improving Efficiency of CNN using Octave Convolution" @default.
- W4253551851 doi "https://doi.org/10.35940/ijrte.f9871.038620" @default.
- W4253551851 hasPublicationYear "2020" @default.
- W4253551851 type Work @default.
- W4253551851 citedByCount "0" @default.
- W4253551851 crossrefType "journal-article" @default.
- W4253551851 hasBestOaLocation W42535518511 @default.
- W4253551851 hasConcept C100921725 @default.
- W4253551851 hasConcept C111919701 @default.
- W4253551851 hasConcept C11413529 @default.
- W4253551851 hasConcept C120665830 @default.
- W4253551851 hasConcept C121332964 @default.
- W4253551851 hasConcept C138885662 @default.
- W4253551851 hasConcept C152124472 @default.
- W4253551851 hasConcept C153180895 @default.
- W4253551851 hasConcept C154945302 @default.
- W4253551851 hasConcept C173608175 @default.
- W4253551851 hasConcept C2776401178 @default.
- W4253551851 hasConcept C3826847 @default.
- W4253551851 hasConcept C41008148 @default.
- W4253551851 hasConcept C41895202 @default.
- W4253551851 hasConcept C45347329 @default.
- W4253551851 hasConcept C50644808 @default.
- W4253551851 hasConcept C81363708 @default.
- W4253551851 hasConcept C85841341 @default.
- W4253551851 hasConceptScore W4253551851C100921725 @default.
- W4253551851 hasConceptScore W4253551851C111919701 @default.
- W4253551851 hasConceptScore W4253551851C11413529 @default.
- W4253551851 hasConceptScore W4253551851C120665830 @default.
- W4253551851 hasConceptScore W4253551851C121332964 @default.
- W4253551851 hasConceptScore W4253551851C138885662 @default.
- W4253551851 hasConceptScore W4253551851C152124472 @default.
- W4253551851 hasConceptScore W4253551851C153180895 @default.
- W4253551851 hasConceptScore W4253551851C154945302 @default.
- W4253551851 hasConceptScore W4253551851C173608175 @default.
- W4253551851 hasConceptScore W4253551851C2776401178 @default.
- W4253551851 hasConceptScore W4253551851C3826847 @default.
- W4253551851 hasConceptScore W4253551851C41008148 @default.
- W4253551851 hasConceptScore W4253551851C41895202 @default.
- W4253551851 hasConceptScore W4253551851C45347329 @default.
- W4253551851 hasConceptScore W4253551851C50644808 @default.
- W4253551851 hasConceptScore W4253551851C81363708 @default.
- W4253551851 hasConceptScore W4253551851C85841341 @default.
- W4253551851 hasIssue "6" @default.
- W4253551851 hasLocation W42535518511 @default.
- W4253551851 hasOpenAccess W4253551851 @default.
- W4253551851 hasPrimaryLocation W42535518511 @default.
- W4253551851 hasRelatedWork W10116868 @default.
- W4253551851 hasRelatedWork W12775346 @default.
- W4253551851 hasRelatedWork W12906885 @default.
- W4253551851 hasRelatedWork W1496815 @default.
- W4253551851 hasRelatedWork W3143391 @default.
- W4253551851 hasRelatedWork W4136762 @default.
- W4253551851 hasRelatedWork W4533635 @default.
- W4253551851 hasRelatedWork W6570580 @default.
- W4253551851 hasRelatedWork W6837029 @default.
- W4253551851 hasRelatedWork W9190101 @default.
- W4253551851 hasVolume "8" @default.
- W4253551851 isParatext "false" @default.
- W4253551851 isRetracted "false" @default.
- W4253551851 workType "article" @default.