Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307545940> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4307545940 endingPage "677" @default.
- W4307545940 startingPage "666" @default.
- W4307545940 abstract "Abstract In the last few years, convolutional neural networks (CNNs) have demonstrated good performance while solving various computer vision problems. However, since CNNs exhibit high computational complexity, signal processing is performed on the server side. To reduce the computational complexity of CNNs for edge computing, a lightweight algorithm, such as a MobileNet, is proposed. Although MobileNet is lighter than other CNN models, it commonly achieves lower classification accuracy. Hence, to find a balance between complexity and accuracy, additional hyperparameters for adjusting the size of the model have recently been proposed. However, significantly increasing the number of parameters makes models dense and unsuitable for devices with limited computational resources. In this study, we propose a novel MobileNet architecture, in which the number of parameters is adaptively increased according to the importance of feature maps. We show that our proposed network achieves better classification accuracy with fewer parameters than the conventional MobileNet." @default.
- W4307545940 created "2022-11-03" @default.
- W4307545940 creator A5011487434 @default.
- W4307545940 creator A5030184835 @default.
- W4307545940 creator A5040011354 @default.
- W4307545940 date "2022-10-25" @default.
- W4307545940 modified "2023-10-17" @default.
- W4307545940 title "A novel MobileNet with selective depth multiplier to compromise complexity and accuracy" @default.
- W4307545940 cites W2097117768 @default.
- W4307545940 cites W2194775991 @default.
- W4307545940 cites W2531409750 @default.
- W4307545940 cites W2884585870 @default.
- W4307545940 cites W2898622774 @default.
- W4307545940 cites W2963125010 @default.
- W4307545940 cites W2963163009 @default.
- W4307545940 cites W2964444894 @default.
- W4307545940 cites W2982083293 @default.
- W4307545940 cites W2982536526 @default.
- W4307545940 cites W3007067769 @default.
- W4307545940 cites W3011426518 @default.
- W4307545940 cites W3011862431 @default.
- W4307545940 cites W3081966421 @default.
- W4307545940 cites W3106397858 @default.
- W4307545940 cites W3112396361 @default.
- W4307545940 cites W3136173504 @default.
- W4307545940 cites W3165026307 @default.
- W4307545940 cites W4210637579 @default.
- W4307545940 doi "https://doi.org/10.4218/etrij.2022-0103" @default.
- W4307545940 hasPublicationYear "2022" @default.
- W4307545940 type Work @default.
- W4307545940 citedByCount "0" @default.
- W4307545940 crossrefType "journal-article" @default.
- W4307545940 hasAuthorship W4307545940A5011487434 @default.
- W4307545940 hasAuthorship W4307545940A5030184835 @default.
- W4307545940 hasAuthorship W4307545940A5040011354 @default.
- W4307545940 hasBestOaLocation W43075459401 @default.
- W4307545940 hasConcept C11413529 @default.
- W4307545940 hasConcept C138885662 @default.
- W4307545940 hasConcept C153180895 @default.
- W4307545940 hasConcept C154945302 @default.
- W4307545940 hasConcept C179799912 @default.
- W4307545940 hasConcept C2776401178 @default.
- W4307545940 hasConcept C41008148 @default.
- W4307545940 hasConcept C41895202 @default.
- W4307545940 hasConcept C50644808 @default.
- W4307545940 hasConcept C81363708 @default.
- W4307545940 hasConcept C8642999 @default.
- W4307545940 hasConceptScore W4307545940C11413529 @default.
- W4307545940 hasConceptScore W4307545940C138885662 @default.
- W4307545940 hasConceptScore W4307545940C153180895 @default.
- W4307545940 hasConceptScore W4307545940C154945302 @default.
- W4307545940 hasConceptScore W4307545940C179799912 @default.
- W4307545940 hasConceptScore W4307545940C2776401178 @default.
- W4307545940 hasConceptScore W4307545940C41008148 @default.
- W4307545940 hasConceptScore W4307545940C41895202 @default.
- W4307545940 hasConceptScore W4307545940C50644808 @default.
- W4307545940 hasConceptScore W4307545940C81363708 @default.
- W4307545940 hasConceptScore W4307545940C8642999 @default.
- W4307545940 hasFunder F4320321237 @default.
- W4307545940 hasIssue "4" @default.
- W4307545940 hasLocation W43075459401 @default.
- W4307545940 hasOpenAccess W4307545940 @default.
- W4307545940 hasPrimaryLocation W43075459401 @default.
- W4307545940 hasRelatedWork W2140186469 @default.
- W4307545940 hasRelatedWork W2775233965 @default.
- W4307545940 hasRelatedWork W3183136280 @default.
- W4307545940 hasRelatedWork W4206951940 @default.
- W4307545940 hasRelatedWork W4280563792 @default.
- W4307545940 hasRelatedWork W4293868382 @default.
- W4307545940 hasRelatedWork W4311551265 @default.
- W4307545940 hasRelatedWork W4318559728 @default.
- W4307545940 hasRelatedWork W4318719684 @default.
- W4307545940 hasRelatedWork W4382602594 @default.
- W4307545940 hasVolume "45" @default.
- W4307545940 isParatext "false" @default.
- W4307545940 isRetracted "false" @default.
- W4307545940 workType "article" @default.