Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092871726> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W3092871726 endingPage "103408" @default.
- W3092871726 startingPage "103408" @default.
- W3092871726 abstract "The performance of convolutional neural networks (CNNs) can be improved by adjusting the interrelationship between channels with attention mechanism. However, attention mechanism in recent advance ignores the effects of different spatial locations in feature maps on attention weights, which makes a great difference to the results of generated channel attentions. In this paper, we propose a novel network optimization module called Channel Reassessment Attention (CRA) which uses channel attentions with spatial information of feature maps to enhance representational power of networks. We employ CRA module to assess channel attentions in different channels, then adaptively refine the final features by channel multiplication between channel attentions and feature maps. CRA is a computational lightweight module and it can be embedded into any architectures of CNNs. The experiments on ImageNet, CIFAR and MS COCO datasets demonstrate that the embedding of CRA module on various networks effectively improves the performance under different evaluation standards." @default.
- W3092871726 created "2020-10-22" @default.
- W3092871726 creator A5036563779 @default.
- W3092871726 creator A5060577972 @default.
- W3092871726 date "2022-04-01" @default.
- W3092871726 modified "2023-10-14" @default.
- W3092871726 title "Convolutional neural network optimization via channel reassessment attention module" @default.
- W3092871726 cites W3028304412 @default.
- W3092871726 cites W3134036510 @default.
- W3092871726 cites W3174763022 @default.
- W3092871726 cites W3200697396 @default.
- W3092871726 doi "https://doi.org/10.1016/j.dsp.2022.103408" @default.
- W3092871726 hasPublicationYear "2022" @default.
- W3092871726 type Work @default.
- W3092871726 sameAs 3092871726 @default.
- W3092871726 citedByCount "3" @default.
- W3092871726 countsByYear W30928717262023 @default.
- W3092871726 crossrefType "journal-article" @default.
- W3092871726 hasAuthorship W3092871726A5036563779 @default.
- W3092871726 hasAuthorship W3092871726A5060577972 @default.
- W3092871726 hasBestOaLocation W30928717262 @default.
- W3092871726 hasConcept C111472728 @default.
- W3092871726 hasConcept C119857082 @default.
- W3092871726 hasConcept C127162648 @default.
- W3092871726 hasConcept C138885662 @default.
- W3092871726 hasConcept C153180895 @default.
- W3092871726 hasConcept C154945302 @default.
- W3092871726 hasConcept C2776401178 @default.
- W3092871726 hasConcept C31258907 @default.
- W3092871726 hasConcept C41008148 @default.
- W3092871726 hasConcept C41608201 @default.
- W3092871726 hasConcept C41895202 @default.
- W3092871726 hasConcept C81363708 @default.
- W3092871726 hasConcept C89611455 @default.
- W3092871726 hasConceptScore W3092871726C111472728 @default.
- W3092871726 hasConceptScore W3092871726C119857082 @default.
- W3092871726 hasConceptScore W3092871726C127162648 @default.
- W3092871726 hasConceptScore W3092871726C138885662 @default.
- W3092871726 hasConceptScore W3092871726C153180895 @default.
- W3092871726 hasConceptScore W3092871726C154945302 @default.
- W3092871726 hasConceptScore W3092871726C2776401178 @default.
- W3092871726 hasConceptScore W3092871726C31258907 @default.
- W3092871726 hasConceptScore W3092871726C41008148 @default.
- W3092871726 hasConceptScore W3092871726C41608201 @default.
- W3092871726 hasConceptScore W3092871726C41895202 @default.
- W3092871726 hasConceptScore W3092871726C81363708 @default.
- W3092871726 hasConceptScore W3092871726C89611455 @default.
- W3092871726 hasLocation W30928717261 @default.
- W3092871726 hasLocation W30928717262 @default.
- W3092871726 hasOpenAccess W3092871726 @default.
- W3092871726 hasPrimaryLocation W30928717261 @default.
- W3092871726 hasRelatedWork W1597848696 @default.
- W3092871726 hasRelatedWork W2351750670 @default.
- W3092871726 hasRelatedWork W2354715126 @default.
- W3092871726 hasRelatedWork W2382213751 @default.
- W3092871726 hasRelatedWork W2382997850 @default.
- W3092871726 hasRelatedWork W2388563748 @default.
- W3092871726 hasRelatedWork W2390968135 @default.
- W3092871726 hasRelatedWork W4293226380 @default.
- W3092871726 hasRelatedWork W2183306018 @default.
- W3092871726 hasRelatedWork W3111219495 @default.
- W3092871726 hasVolume "123" @default.
- W3092871726 isParatext "false" @default.
- W3092871726 isRetracted "false" @default.
- W3092871726 magId "3092871726" @default.
- W3092871726 workType "article" @default.