Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128842017> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W3128842017 abstract "Capsule Networks (CapsNets) are the new generation of classifiers with several advantages over the previous ones. Such advantages include higher robustness to affine transformed datasets and detection of overlapping images. CapsNets, while obtaining state-of-the-art accuracy on the MNIST digit recognition dataset, fall behind Convolutional Neural Networks (CNNs) for other datasets. Moreover, CapsNets are slow compared to CNNs. In this work, we propose Convolutional Fully Connected (CFC) CapsNet as an alternative enhanced architecture to conventional CapsNet [8]. CFC-CapsNet is a more efficient network: training and testing are performed faster and a slightly higher accuracy is achieved compared to the conventional CapsNet. CFC-CapsNet includes fewer trainable weights (parameters) and therefore is more efficient in terms of memory usage. The code for CFC-CapsNet is available on Github 1." @default.
- W3128842017 created "2021-02-15" @default.
- W3128842017 creator A5000153604 @default.
- W3128842017 creator A5052700161 @default.
- W3128842017 date "2021-01-18" @default.
- W3128842017 modified "2023-09-26" @default.
- W3128842017 title "Convolutional Fully-Connected Capsule Network (CFC-CapsNet)" @default.
- W3128842017 cites W2895526696 @default.
- W3128842017 cites W2965481041 @default.
- W3128842017 cites W3098854735 @default.
- W3128842017 doi "https://doi.org/10.1145/3441110.3441148" @default.
- W3128842017 hasPublicationYear "2021" @default.
- W3128842017 type Work @default.
- W3128842017 sameAs 3128842017 @default.
- W3128842017 citedByCount "4" @default.
- W3128842017 countsByYear W31288420172022 @default.
- W3128842017 crossrefType "proceedings-article" @default.
- W3128842017 hasAuthorship W3128842017A5000153604 @default.
- W3128842017 hasAuthorship W3128842017A5052700161 @default.
- W3128842017 hasConcept C104317684 @default.
- W3128842017 hasConcept C108583219 @default.
- W3128842017 hasConcept C11413529 @default.
- W3128842017 hasConcept C153180895 @default.
- W3128842017 hasConcept C154945302 @default.
- W3128842017 hasConcept C157899210 @default.
- W3128842017 hasConcept C185592680 @default.
- W3128842017 hasConcept C190502265 @default.
- W3128842017 hasConcept C202444582 @default.
- W3128842017 hasConcept C33923547 @default.
- W3128842017 hasConcept C41008148 @default.
- W3128842017 hasConcept C55493867 @default.
- W3128842017 hasConcept C57273362 @default.
- W3128842017 hasConcept C63479239 @default.
- W3128842017 hasConcept C81363708 @default.
- W3128842017 hasConcept C92757383 @default.
- W3128842017 hasConceptScore W3128842017C104317684 @default.
- W3128842017 hasConceptScore W3128842017C108583219 @default.
- W3128842017 hasConceptScore W3128842017C11413529 @default.
- W3128842017 hasConceptScore W3128842017C153180895 @default.
- W3128842017 hasConceptScore W3128842017C154945302 @default.
- W3128842017 hasConceptScore W3128842017C157899210 @default.
- W3128842017 hasConceptScore W3128842017C185592680 @default.
- W3128842017 hasConceptScore W3128842017C190502265 @default.
- W3128842017 hasConceptScore W3128842017C202444582 @default.
- W3128842017 hasConceptScore W3128842017C33923547 @default.
- W3128842017 hasConceptScore W3128842017C41008148 @default.
- W3128842017 hasConceptScore W3128842017C55493867 @default.
- W3128842017 hasConceptScore W3128842017C57273362 @default.
- W3128842017 hasConceptScore W3128842017C63479239 @default.
- W3128842017 hasConceptScore W3128842017C81363708 @default.
- W3128842017 hasConceptScore W3128842017C92757383 @default.
- W3128842017 hasLocation W31288420171 @default.
- W3128842017 hasOpenAccess W3128842017 @default.
- W3128842017 hasPrimaryLocation W31288420171 @default.
- W3128842017 hasRelatedWork W2731899572 @default.
- W3128842017 hasRelatedWork W2911373680 @default.
- W3128842017 hasRelatedWork W2947175736 @default.
- W3128842017 hasRelatedWork W3133861977 @default.
- W3128842017 hasRelatedWork W3156786002 @default.
- W3128842017 hasRelatedWork W3208266890 @default.
- W3128842017 hasRelatedWork W4200173597 @default.
- W3128842017 hasRelatedWork W4309224979 @default.
- W3128842017 hasRelatedWork W4312417841 @default.
- W3128842017 hasRelatedWork W4321369474 @default.
- W3128842017 isParatext "false" @default.
- W3128842017 isRetracted "false" @default.
- W3128842017 magId "3128842017" @default.
- W3128842017 workType "article" @default.