Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174143002> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3174143002 abstract "This paper investigates impacts of kernel factorization on different resized images in object recognition based on three inception-block modules of inception convolutional neural networks (ICNNs), namely ICONV3 and ICONV131. The ICONV3 employs 3×3 kernel-size convolutions according to each inception-block; whereas the ICONV131 equivalently uses 1×3 and 3×1, replacing one 3×3 convolutions. The experiments rely on two different resized 50×50, 100×100 pixels regarding 60,000 samples of 32×32, in 10-class benchmark CIFAR-10 image dataset. Recognition performance evaluations depend on averages of precision, recall, F1 and accuracy scores, based on 10-fold cross validation for bias reduction purpose. The results indicates approximate 5% obviously better recognition accuracy of using larger resized of CIFAR-10 than small ones according to both ICONV3 and ICONV131 models. Only few 0.2% to 0.3% different recognition performance are exhibited between ICONV3 and ICONV131 for both large and small resized images. This may cause one to say ICONV131 may be preferred to ICONV3 due to about 3.6% and 6% greater parameters used in ICONV3 than ICONV131, respectively regarding 50×50 and 100×100 resized images." @default.
- W3174143002 created "2021-07-05" @default.
- W3174143002 creator A5033047442 @default.
- W3174143002 creator A5040257808 @default.
- W3174143002 date "2021-05-19" @default.
- W3174143002 modified "2023-09-25" @default.
- W3174143002 title "Impacts of Kernel Factorization on Different Resized Images in Object Recognition Base on Inception Convolutional Neural Network" @default.
- W3174143002 cites W1686810756 @default.
- W3174143002 cites W2097117768 @default.
- W3174143002 cites W2117539524 @default.
- W3174143002 cites W2163605009 @default.
- W3174143002 cites W2183341477 @default.
- W3174143002 cites W2790156448 @default.
- W3174143002 cites W2893345206 @default.
- W3174143002 cites W2962850395 @default.
- W3174143002 cites W2996500604 @default.
- W3174143002 cites W3003544448 @default.
- W3174143002 doi "https://doi.org/10.1109/ecti-con51831.2021.9454729" @default.
- W3174143002 hasPublicationYear "2021" @default.
- W3174143002 type Work @default.
- W3174143002 sameAs 3174143002 @default.
- W3174143002 citedByCount "0" @default.
- W3174143002 crossrefType "proceedings-article" @default.
- W3174143002 hasAuthorship W3174143002A5033047442 @default.
- W3174143002 hasAuthorship W3174143002A5040257808 @default.
- W3174143002 hasConcept C114614502 @default.
- W3174143002 hasConcept C13280743 @default.
- W3174143002 hasConcept C153180895 @default.
- W3174143002 hasConcept C154945302 @default.
- W3174143002 hasConcept C160633673 @default.
- W3174143002 hasConcept C185798385 @default.
- W3174143002 hasConcept C205649164 @default.
- W3174143002 hasConcept C2524010 @default.
- W3174143002 hasConcept C2777210771 @default.
- W3174143002 hasConcept C2781238097 @default.
- W3174143002 hasConcept C33923547 @default.
- W3174143002 hasConcept C41008148 @default.
- W3174143002 hasConcept C64876066 @default.
- W3174143002 hasConcept C74193536 @default.
- W3174143002 hasConcept C81363708 @default.
- W3174143002 hasConceptScore W3174143002C114614502 @default.
- W3174143002 hasConceptScore W3174143002C13280743 @default.
- W3174143002 hasConceptScore W3174143002C153180895 @default.
- W3174143002 hasConceptScore W3174143002C154945302 @default.
- W3174143002 hasConceptScore W3174143002C160633673 @default.
- W3174143002 hasConceptScore W3174143002C185798385 @default.
- W3174143002 hasConceptScore W3174143002C205649164 @default.
- W3174143002 hasConceptScore W3174143002C2524010 @default.
- W3174143002 hasConceptScore W3174143002C2777210771 @default.
- W3174143002 hasConceptScore W3174143002C2781238097 @default.
- W3174143002 hasConceptScore W3174143002C33923547 @default.
- W3174143002 hasConceptScore W3174143002C41008148 @default.
- W3174143002 hasConceptScore W3174143002C64876066 @default.
- W3174143002 hasConceptScore W3174143002C74193536 @default.
- W3174143002 hasConceptScore W3174143002C81363708 @default.
- W3174143002 hasLocation W31741430021 @default.
- W3174143002 hasOpenAccess W3174143002 @default.
- W3174143002 hasPrimaryLocation W31741430021 @default.
- W3174143002 hasRelatedWork W10405577 @default.
- W3174143002 hasRelatedWork W11453422 @default.
- W3174143002 hasRelatedWork W12729829 @default.
- W3174143002 hasRelatedWork W13058890 @default.
- W3174143002 hasRelatedWork W14879752 @default.
- W3174143002 hasRelatedWork W2380338 @default.
- W3174143002 hasRelatedWork W4326812 @default.
- W3174143002 hasRelatedWork W9190101 @default.
- W3174143002 hasRelatedWork W9813265 @default.
- W3174143002 hasRelatedWork W11907932 @default.
- W3174143002 isParatext "false" @default.
- W3174143002 isRetracted "false" @default.
- W3174143002 magId "3174143002" @default.
- W3174143002 workType "article" @default.