Matches in SemOpenAlex for { <https://semopenalex.org/work/W3002091291> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3002091291 endingPage "398" @default.
- W3002091291 startingPage "391" @default.
- W3002091291 abstract "Neural networks have become a standard for classifying images. However, by their very nature, their internal data representation remains opaque. To solve this dilemma, attention mechanisms have recently been introduced. They help to highlight regions in input data that have been used for a network’s classification decision. This article presents two attention architectures for the classification of medical images. Firstly, we are explaining a simple architecture which creates one attention map that is used for all classes. Secondly, we introduce an architecture that creates an attention map for each class. This is done by creating two U-nets - one for attention and one for classification - and then multiplying these two maps together. We show that our architectures well meet the baseline of standard convolutional classifications while at the same time increasing their explainability." @default.
- W3002091291 created "2020-01-30" @default.
- W3002091291 creator A5004096188 @default.
- W3002091291 creator A5020580211 @default.
- W3002091291 creator A5046431175 @default.
- W3002091291 creator A5046963723 @default.
- W3002091291 creator A5056550009 @default.
- W3002091291 date "2020-01-01" @default.
- W3002091291 modified "2023-09-26" @default.
- W3002091291 title "Convolutional Attention on Images for Locating Macular Edema" @default.
- W3002091291 cites W1677182931 @default.
- W3002091291 cites W2790963474 @default.
- W3002091291 cites W2891285531 @default.
- W3002091291 cites W2894802018 @default.
- W3002091291 doi "https://doi.org/10.1007/978-3-030-39343-4_33" @default.
- W3002091291 hasPublicationYear "2020" @default.
- W3002091291 type Work @default.
- W3002091291 sameAs 3002091291 @default.
- W3002091291 citedByCount "1" @default.
- W3002091291 countsByYear W30020912912023 @default.
- W3002091291 crossrefType "book-chapter" @default.
- W3002091291 hasAuthorship W3002091291A5004096188 @default.
- W3002091291 hasAuthorship W3002091291A5020580211 @default.
- W3002091291 hasAuthorship W3002091291A5046431175 @default.
- W3002091291 hasAuthorship W3002091291A5046963723 @default.
- W3002091291 hasAuthorship W3002091291A5056550009 @default.
- W3002091291 hasConcept C111472728 @default.
- W3002091291 hasConcept C115961682 @default.
- W3002091291 hasConcept C120665830 @default.
- W3002091291 hasConcept C121332964 @default.
- W3002091291 hasConcept C123657996 @default.
- W3002091291 hasConcept C138885662 @default.
- W3002091291 hasConcept C153180895 @default.
- W3002091291 hasConcept C154945302 @default.
- W3002091291 hasConcept C166957645 @default.
- W3002091291 hasConcept C17744445 @default.
- W3002091291 hasConcept C199539241 @default.
- W3002091291 hasConcept C205649164 @default.
- W3002091291 hasConcept C2524010 @default.
- W3002091291 hasConcept C2776359362 @default.
- W3002091291 hasConcept C2777212361 @default.
- W3002091291 hasConcept C2778496695 @default.
- W3002091291 hasConcept C2780586882 @default.
- W3002091291 hasConcept C33923547 @default.
- W3002091291 hasConcept C41008148 @default.
- W3002091291 hasConcept C60056205 @default.
- W3002091291 hasConcept C75294576 @default.
- W3002091291 hasConcept C81363708 @default.
- W3002091291 hasConcept C94625758 @default.
- W3002091291 hasConceptScore W3002091291C111472728 @default.
- W3002091291 hasConceptScore W3002091291C115961682 @default.
- W3002091291 hasConceptScore W3002091291C120665830 @default.
- W3002091291 hasConceptScore W3002091291C121332964 @default.
- W3002091291 hasConceptScore W3002091291C123657996 @default.
- W3002091291 hasConceptScore W3002091291C138885662 @default.
- W3002091291 hasConceptScore W3002091291C153180895 @default.
- W3002091291 hasConceptScore W3002091291C154945302 @default.
- W3002091291 hasConceptScore W3002091291C166957645 @default.
- W3002091291 hasConceptScore W3002091291C17744445 @default.
- W3002091291 hasConceptScore W3002091291C199539241 @default.
- W3002091291 hasConceptScore W3002091291C205649164 @default.
- W3002091291 hasConceptScore W3002091291C2524010 @default.
- W3002091291 hasConceptScore W3002091291C2776359362 @default.
- W3002091291 hasConceptScore W3002091291C2777212361 @default.
- W3002091291 hasConceptScore W3002091291C2778496695 @default.
- W3002091291 hasConceptScore W3002091291C2780586882 @default.
- W3002091291 hasConceptScore W3002091291C33923547 @default.
- W3002091291 hasConceptScore W3002091291C41008148 @default.
- W3002091291 hasConceptScore W3002091291C60056205 @default.
- W3002091291 hasConceptScore W3002091291C75294576 @default.
- W3002091291 hasConceptScore W3002091291C81363708 @default.
- W3002091291 hasConceptScore W3002091291C94625758 @default.
- W3002091291 hasLocation W30020912911 @default.
- W3002091291 hasOpenAccess W3002091291 @default.
- W3002091291 hasPrimaryLocation W30020912911 @default.
- W3002091291 hasRelatedWork W1982635469 @default.
- W3002091291 hasRelatedWork W2732542196 @default.
- W3002091291 hasRelatedWork W2760085659 @default.
- W3002091291 hasRelatedWork W2912288872 @default.
- W3002091291 hasRelatedWork W2940661641 @default.
- W3002091291 hasRelatedWork W2940977206 @default.
- W3002091291 hasRelatedWork W2964383635 @default.
- W3002091291 hasRelatedWork W3086857729 @default.
- W3002091291 hasRelatedWork W3153891452 @default.
- W3002091291 hasRelatedWork W4207027803 @default.
- W3002091291 isParatext "false" @default.
- W3002091291 isRetracted "false" @default.
- W3002091291 magId "3002091291" @default.
- W3002091291 workType "book-chapter" @default.