Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953334571> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2953334571 endingPage "3090" @default.
- W2953334571 startingPage "3080" @default.
- W2953334571 abstract "Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to design models that generalize well under certain resource constraints, e.g. the number of parameters. In this paper, we propose a simple way to improve the capacity of any CNN model having large-scale features, without adding more parameters. In particular, we modify a standard convolutional layer to have a new functionality of channel-selectivity, so that the layer is trained to select important channels to re-distribute their parameters. Our experimental results under various CNN architectures and datasets demonstrate that the proposed new convolutional layer allows new optima that generalize better via efficient resource utilization, compared to the baseline." @default.
- W2953334571 created "2019-06-27" @default.
- W2953334571 creator A5035397475 @default.
- W2953334571 creator A5045815823 @default.
- W2953334571 date "2019-05-24" @default.
- W2953334571 modified "2023-09-26" @default.
- W2953334571 title "Training CNNs with Selective Allocation of Channels" @default.
- W2953334571 hasPublicationYear "2019" @default.
- W2953334571 type Work @default.
- W2953334571 sameAs 2953334571 @default.
- W2953334571 citedByCount "6" @default.
- W2953334571 countsByYear W29533345712019 @default.
- W2953334571 countsByYear W29533345712020 @default.
- W2953334571 countsByYear W29533345712021 @default.
- W2953334571 crossrefType "proceedings-article" @default.
- W2953334571 hasAuthorship W2953334571A5035397475 @default.
- W2953334571 hasAuthorship W2953334571A5045815823 @default.
- W2953334571 hasConcept C108583219 @default.
- W2953334571 hasConcept C111472728 @default.
- W2953334571 hasConcept C113775141 @default.
- W2953334571 hasConcept C119857082 @default.
- W2953334571 hasConcept C127162648 @default.
- W2953334571 hasConcept C138885662 @default.
- W2953334571 hasConcept C154945302 @default.
- W2953334571 hasConcept C178790620 @default.
- W2953334571 hasConcept C185592680 @default.
- W2953334571 hasConcept C2779227376 @default.
- W2953334571 hasConcept C2780586882 @default.
- W2953334571 hasConcept C29202148 @default.
- W2953334571 hasConcept C31258907 @default.
- W2953334571 hasConcept C41008148 @default.
- W2953334571 hasConcept C81363708 @default.
- W2953334571 hasConceptScore W2953334571C108583219 @default.
- W2953334571 hasConceptScore W2953334571C111472728 @default.
- W2953334571 hasConceptScore W2953334571C113775141 @default.
- W2953334571 hasConceptScore W2953334571C119857082 @default.
- W2953334571 hasConceptScore W2953334571C127162648 @default.
- W2953334571 hasConceptScore W2953334571C138885662 @default.
- W2953334571 hasConceptScore W2953334571C154945302 @default.
- W2953334571 hasConceptScore W2953334571C178790620 @default.
- W2953334571 hasConceptScore W2953334571C185592680 @default.
- W2953334571 hasConceptScore W2953334571C2779227376 @default.
- W2953334571 hasConceptScore W2953334571C2780586882 @default.
- W2953334571 hasConceptScore W2953334571C29202148 @default.
- W2953334571 hasConceptScore W2953334571C31258907 @default.
- W2953334571 hasConceptScore W2953334571C41008148 @default.
- W2953334571 hasConceptScore W2953334571C81363708 @default.
- W2953334571 hasLocation W29533345711 @default.
- W2953334571 hasOpenAccess W2953334571 @default.
- W2953334571 hasPrimaryLocation W29533345711 @default.
- W2953334571 hasRelatedWork W2194775991 @default.
- W2953334571 hasRelatedWork W2269278629 @default.
- W2953334571 hasRelatedWork W2618353736 @default.
- W2953334571 hasRelatedWork W2741546454 @default.
- W2953334571 hasRelatedWork W2758217051 @default.
- W2953334571 hasRelatedWork W2795923793 @default.
- W2953334571 hasRelatedWork W2911089685 @default.
- W2953334571 hasRelatedWork W2944336669 @default.
- W2953334571 hasRelatedWork W2951414223 @default.
- W2953334571 hasRelatedWork W2953308748 @default.
- W2953334571 hasRelatedWork W2954248940 @default.
- W2953334571 hasRelatedWork W2963446712 @default.
- W2953334571 hasRelatedWork W2968452475 @default.
- W2953334571 hasRelatedWork W2968593283 @default.
- W2953334571 hasRelatedWork W2991261627 @default.
- W2953334571 hasRelatedWork W3047783818 @default.
- W2953334571 hasRelatedWork W3086425440 @default.
- W2953334571 hasRelatedWork W3096108976 @default.
- W2953334571 hasRelatedWork W3102849520 @default.
- W2953334571 hasRelatedWork W3103843209 @default.
- W2953334571 isParatext "false" @default.
- W2953334571 isRetracted "false" @default.
- W2953334571 magId "2953334571" @default.
- W2953334571 workType "article" @default.