Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786128974> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2786128974 abstract "Convolutional Neural Networks continuously advance the progress of 2D and 3D image and object classification. The steadfast usage of this algorithm requires constant evaluation and upgrading of foundational concepts to maintain progress. Network regularization techniques typically focus on convolutional layer operations, while leaving pooling layer operations without suitable options. We introduce Wavelet Pooling as another alternative to traditional neighborhood pooling. This method decomposes features into a second level decomposition, and discards the first-level subbands to reduce feature dimensions. This method addresses the overfitting problem encountered by max pooling, while reducing features in a more structurally compact manner than pooling via neighborhood regions. Experimental results on four benchmark classification datasets demonstrate our proposed method outperforms or performs comparatively with methods like max, mean, mixed, and stochastic pooling." @default.
- W2786128974 created "2018-02-23" @default.
- W2786128974 creator A5005873257 @default.
- W2786128974 creator A5061558169 @default.
- W2786128974 date "2018-02-15" @default.
- W2786128974 modified "2023-10-04" @default.
- W2786128974 title "Wavelet Pooling for Convolutional Neural Networks" @default.
- W2786128974 hasPublicationYear "2018" @default.
- W2786128974 type Work @default.
- W2786128974 sameAs 2786128974 @default.
- W2786128974 citedByCount "31" @default.
- W2786128974 countsByYear W27861289742017 @default.
- W2786128974 countsByYear W27861289742018 @default.
- W2786128974 countsByYear W27861289742019 @default.
- W2786128974 countsByYear W27861289742020 @default.
- W2786128974 countsByYear W27861289742021 @default.
- W2786128974 countsByYear W27861289742022 @default.
- W2786128974 crossrefType "proceedings-article" @default.
- W2786128974 hasAuthorship W2786128974A5005873257 @default.
- W2786128974 hasAuthorship W2786128974A5061558169 @default.
- W2786128974 hasConcept C115961682 @default.
- W2786128974 hasConcept C119857082 @default.
- W2786128974 hasConcept C124101348 @default.
- W2786128974 hasConcept C13280743 @default.
- W2786128974 hasConcept C138885662 @default.
- W2786128974 hasConcept C153180895 @default.
- W2786128974 hasConcept C154945302 @default.
- W2786128974 hasConcept C185798385 @default.
- W2786128974 hasConcept C205649164 @default.
- W2786128974 hasConcept C22019652 @default.
- W2786128974 hasConcept C2776401178 @default.
- W2786128974 hasConcept C41008148 @default.
- W2786128974 hasConcept C41895202 @default.
- W2786128974 hasConcept C47432892 @default.
- W2786128974 hasConcept C50644808 @default.
- W2786128974 hasConcept C70437156 @default.
- W2786128974 hasConcept C75294576 @default.
- W2786128974 hasConcept C81363708 @default.
- W2786128974 hasConceptScore W2786128974C115961682 @default.
- W2786128974 hasConceptScore W2786128974C119857082 @default.
- W2786128974 hasConceptScore W2786128974C124101348 @default.
- W2786128974 hasConceptScore W2786128974C13280743 @default.
- W2786128974 hasConceptScore W2786128974C138885662 @default.
- W2786128974 hasConceptScore W2786128974C153180895 @default.
- W2786128974 hasConceptScore W2786128974C154945302 @default.
- W2786128974 hasConceptScore W2786128974C185798385 @default.
- W2786128974 hasConceptScore W2786128974C205649164 @default.
- W2786128974 hasConceptScore W2786128974C22019652 @default.
- W2786128974 hasConceptScore W2786128974C2776401178 @default.
- W2786128974 hasConceptScore W2786128974C41008148 @default.
- W2786128974 hasConceptScore W2786128974C41895202 @default.
- W2786128974 hasConceptScore W2786128974C47432892 @default.
- W2786128974 hasConceptScore W2786128974C50644808 @default.
- W2786128974 hasConceptScore W2786128974C70437156 @default.
- W2786128974 hasConceptScore W2786128974C75294576 @default.
- W2786128974 hasConceptScore W2786128974C81363708 @default.
- W2786128974 hasLocation W27861289741 @default.
- W2786128974 hasOpenAccess W2786128974 @default.
- W2786128974 hasPrimaryLocation W27861289741 @default.
- W2786128974 hasRelatedWork W1686810756 @default.
- W2786128974 hasRelatedWork W1840106123 @default.
- W2786128974 hasRelatedWork W1901129140 @default.
- W2786128974 hasRelatedWork W1907282891 @default.
- W2786128974 hasRelatedWork W2072072671 @default.
- W2786128974 hasRelatedWork W2095705004 @default.
- W2786128974 hasRelatedWork W2099471712 @default.
- W2786128974 hasRelatedWork W2108598243 @default.
- W2786128974 hasRelatedWork W2112796928 @default.
- W2786128974 hasRelatedWork W2132984323 @default.
- W2786128974 hasRelatedWork W2162931300 @default.
- W2786128974 hasRelatedWork W2163605009 @default.
- W2786128974 hasRelatedWork W2194775991 @default.
- W2786128974 hasRelatedWork W2737081839 @default.
- W2786128974 hasRelatedWork W2776107444 @default.
- W2786128974 hasRelatedWork W2899771611 @default.
- W2786128974 hasRelatedWork W2963446712 @default.
- W2786128974 hasRelatedWork W2963919294 @default.
- W2786128974 hasRelatedWork W2964012402 @default.
- W2786128974 hasRelatedWork W3118608800 @default.
- W2786128974 isParatext "false" @default.
- W2786128974 isRetracted "false" @default.
- W2786128974 magId "2786128974" @default.
- W2786128974 workType "article" @default.