Matches in SemOpenAlex for { <https://semopenalex.org/work/W2795475802> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2795475802 abstract "In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that only retains the element with maximum activation, while completely discarding the information contained in other elements in a pooling region. To address this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is introduced in this work. OPN rearranges all the elements of a pooling region in a sequence and assigns different weights to these elements based upon their orders in the sequence, where the weights are learned via the gradient-based optimisation. The results of our small-scale experiments on image classification task demonstrate that this scheme leads to a consistent improvement in the accuracy over max-pooling operation. This improvement is expected to increase in deeper networks, where several layers of pooling become necessary." @default.
- W2795475802 created "2018-04-13" @default.
- W2795475802 creator A5014511851 @default.
- W2795475802 date "2018-04-08" @default.
- W2795475802 modified "2023-09-27" @default.
- W2795475802 title "Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps." @default.
- W2795475802 cites W1523493493 @default.
- W2795475802 cites W1799366690 @default.
- W2795475802 cites W1904365287 @default.
- W2795475802 cites W1907282891 @default.
- W2795475802 cites W1926645898 @default.
- W2795475802 cites W2112796928 @default.
- W2795475802 cites W2117951582 @default.
- W2795475802 cites W2160692033 @default.
- W2795475802 cites W2163605009 @default.
- W2795475802 cites W2194775991 @default.
- W2795475802 cites W2306289963 @default.
- W2795475802 cites W2484273982 @default.
- W2795475802 cites W2559156603 @default.
- W2795475802 cites W2626256601 @default.
- W2795475802 cites W2785994986 @default.
- W2795475802 cites W2963382180 @default.
- W2795475802 cites W2963420686 @default.
- W2795475802 cites W3143797459 @default.
- W2795475802 cites W639708223 @default.
- W2795475802 hasPublicationYear "2018" @default.
- W2795475802 type Work @default.
- W2795475802 sameAs 2795475802 @default.
- W2795475802 citedByCount "1" @default.
- W2795475802 countsByYear W27954758022020 @default.
- W2795475802 crossrefType "posted-content" @default.
- W2795475802 hasAuthorship W2795475802A5014511851 @default.
- W2795475802 hasConcept C110384440 @default.
- W2795475802 hasConcept C11413529 @default.
- W2795475802 hasConcept C115961682 @default.
- W2795475802 hasConcept C124101348 @default.
- W2795475802 hasConcept C138885662 @default.
- W2795475802 hasConcept C142575187 @default.
- W2795475802 hasConcept C153180895 @default.
- W2795475802 hasConcept C154945302 @default.
- W2795475802 hasConcept C2524010 @default.
- W2795475802 hasConcept C2776401178 @default.
- W2795475802 hasConcept C2778112365 @default.
- W2795475802 hasConcept C33923547 @default.
- W2795475802 hasConcept C41008148 @default.
- W2795475802 hasConcept C41895202 @default.
- W2795475802 hasConcept C54355233 @default.
- W2795475802 hasConcept C70437156 @default.
- W2795475802 hasConcept C81363708 @default.
- W2795475802 hasConcept C86803240 @default.
- W2795475802 hasConceptScore W2795475802C110384440 @default.
- W2795475802 hasConceptScore W2795475802C11413529 @default.
- W2795475802 hasConceptScore W2795475802C115961682 @default.
- W2795475802 hasConceptScore W2795475802C124101348 @default.
- W2795475802 hasConceptScore W2795475802C138885662 @default.
- W2795475802 hasConceptScore W2795475802C142575187 @default.
- W2795475802 hasConceptScore W2795475802C153180895 @default.
- W2795475802 hasConceptScore W2795475802C154945302 @default.
- W2795475802 hasConceptScore W2795475802C2524010 @default.
- W2795475802 hasConceptScore W2795475802C2776401178 @default.
- W2795475802 hasConceptScore W2795475802C2778112365 @default.
- W2795475802 hasConceptScore W2795475802C33923547 @default.
- W2795475802 hasConceptScore W2795475802C41008148 @default.
- W2795475802 hasConceptScore W2795475802C41895202 @default.
- W2795475802 hasConceptScore W2795475802C54355233 @default.
- W2795475802 hasConceptScore W2795475802C70437156 @default.
- W2795475802 hasConceptScore W2795475802C81363708 @default.
- W2795475802 hasConceptScore W2795475802C86803240 @default.
- W2795475802 hasLocation W27954758021 @default.
- W2795475802 hasOpenAccess W2795475802 @default.
- W2795475802 hasPrimaryLocation W27954758021 @default.
- W2795475802 hasRelatedWork W2198082746 @default.
- W2795475802 hasRelatedWork W2478974939 @default.
- W2795475802 hasRelatedWork W2559767192 @default.
- W2795475802 hasRelatedWork W2561856247 @default.
- W2795475802 hasRelatedWork W2724116567 @default.
- W2795475802 hasRelatedWork W2793173694 @default.
- W2795475802 hasRelatedWork W2804847616 @default.
- W2795475802 hasRelatedWork W2936114877 @default.
- W2795475802 hasRelatedWork W2950204777 @default.
- W2795475802 hasRelatedWork W2950475844 @default.
- W2795475802 hasRelatedWork W2995796453 @default.
- W2795475802 hasRelatedWork W3047301547 @default.
- W2795475802 hasRelatedWork W3092448552 @default.
- W2795475802 hasRelatedWork W3101685104 @default.
- W2795475802 hasRelatedWork W3103803535 @default.
- W2795475802 hasRelatedWork W3167056225 @default.
- W2795475802 hasRelatedWork W3175393820 @default.
- W2795475802 hasRelatedWork W3195676581 @default.
- W2795475802 hasRelatedWork W3196423891 @default.
- W2795475802 hasRelatedWork W2337248289 @default.
- W2795475802 isParatext "false" @default.
- W2795475802 isRetracted "false" @default.
- W2795475802 magId "2795475802" @default.
- W2795475802 workType "article" @default.