Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003696480> ?p ?o ?g. }
- W3003696480 abstract "Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue, yet limited research effort has been reported concerning their user evaluation. In this paper, we report on an online between-group user study designed to evaluate the performance of - a popular explanation algorithm for image classification applications of CNNs. Our results indicate that saliency maps produced by the LRP algorithm helped participants to learn about some specific image features the system is sensitive to. However, the maps seem to provide very limited help for participants to anticipate the network's output for new images. Drawing on our findings, we highlight implications for design and further research on explainable AI. In particular, we argue the HCI and AI communities should look beyond instance-level explanations." @default.
- W3003696480 created "2020-02-07" @default.
- W3003696480 creator A5020935970 @default.
- W3003696480 creator A5032970359 @default.
- W3003696480 creator A5041918106 @default.
- W3003696480 creator A5070938834 @default.
- W3003696480 creator A5072897829 @default.
- W3003696480 date "2020-02-03" @default.
- W3003696480 modified "2023-10-01" @default.
- W3003696480 title "Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study." @default.
- W3003696480 cites W1663973292 @default.
- W3003696480 cites W1686810756 @default.
- W3003696480 cites W1787224781 @default.
- W3003696480 cites W1982451429 @default.
- W3003696480 cites W2008084531 @default.
- W3003696480 cites W2016839846 @default.
- W3003696480 cites W2037227137 @default.
- W3003696480 cites W2042316632 @default.
- W3003696480 cites W2053075547 @default.
- W3003696480 cites W2056621158 @default.
- W3003696480 cites W2087061903 @default.
- W3003696480 cites W2108598243 @default.
- W3003696480 cites W2108818539 @default.
- W3003696480 cites W2110171129 @default.
- W3003696480 cites W2134584261 @default.
- W3003696480 cites W2134874052 @default.
- W3003696480 cites W2154157725 @default.
- W3003696480 cites W2160385283 @default.
- W3003696480 cites W2232870322 @default.
- W3003696480 cites W2237502368 @default.
- W3003696480 cites W2282821441 @default.
- W3003696480 cites W2332488709 @default.
- W3003696480 cites W2468538938 @default.
- W3003696480 cites W2551317447 @default.
- W3003696480 cites W2554719826 @default.
- W3003696480 cites W2594475271 @default.
- W3003696480 cites W2785327160 @default.
- W3003696480 cites W2788362053 @default.
- W3003696480 cites W2795530988 @default.
- W3003696480 cites W2796885425 @default.
- W3003696480 cites W2892341857 @default.
- W3003696480 cites W2896487960 @default.
- W3003696480 cites W2916797267 @default.
- W3003696480 cites W2918066172 @default.
- W3003696480 cites W2943285501 @default.
- W3003696480 cites W2946185430 @default.
- W3003696480 cites W2962772482 @default.
- W3003696480 cites W2962790223 @default.
- W3003696480 cites W2962851944 @default.
- W3003696480 cites W2963464195 @default.
- W3003696480 cites W2963503775 @default.
- W3003696480 cites W2963673242 @default.
- W3003696480 hasPublicationYear "2020" @default.
- W3003696480 type Work @default.
- W3003696480 sameAs 3003696480 @default.
- W3003696480 citedByCount "7" @default.
- W3003696480 countsByYear W30036964802020 @default.
- W3003696480 countsByYear W30036964802021 @default.
- W3003696480 crossrefType "posted-content" @default.
- W3003696480 hasAuthorship W3003696480A5020935970 @default.
- W3003696480 hasAuthorship W3003696480A5032970359 @default.
- W3003696480 hasAuthorship W3003696480A5041918106 @default.
- W3003696480 hasAuthorship W3003696480A5070938834 @default.
- W3003696480 hasAuthorship W3003696480A5072897829 @default.
- W3003696480 hasConcept C115961682 @default.
- W3003696480 hasConcept C119857082 @default.
- W3003696480 hasConcept C127413603 @default.
- W3003696480 hasConcept C146978453 @default.
- W3003696480 hasConcept C154945302 @default.
- W3003696480 hasConcept C204323151 @default.
- W3003696480 hasConcept C41008148 @default.
- W3003696480 hasConcept C81363708 @default.
- W3003696480 hasConceptScore W3003696480C115961682 @default.
- W3003696480 hasConceptScore W3003696480C119857082 @default.
- W3003696480 hasConceptScore W3003696480C127413603 @default.
- W3003696480 hasConceptScore W3003696480C146978453 @default.
- W3003696480 hasConceptScore W3003696480C154945302 @default.
- W3003696480 hasConceptScore W3003696480C204323151 @default.
- W3003696480 hasConceptScore W3003696480C41008148 @default.
- W3003696480 hasConceptScore W3003696480C81363708 @default.
- W3003696480 hasLocation W30036964801 @default.
- W3003696480 hasOpenAccess W3003696480 @default.
- W3003696480 hasPrimaryLocation W30036964801 @default.
- W3003696480 hasRelatedWork W1994606570 @default.
- W3003696480 hasRelatedWork W2896657282 @default.
- W3003696480 hasRelatedWork W2962851944 @default.
- W3003696480 hasRelatedWork W2963095307 @default.
- W3003696480 hasRelatedWork W2969316698 @default.
- W3003696480 hasRelatedWork W2983256121 @default.
- W3003696480 hasRelatedWork W3010300896 @default.
- W3003696480 hasRelatedWork W3023163568 @default.
- W3003696480 hasRelatedWork W3025915648 @default.
- W3003696480 hasRelatedWork W3044826997 @default.
- W3003696480 hasRelatedWork W3100699829 @default.
- W3003696480 hasRelatedWork W3112040275 @default.
- W3003696480 hasRelatedWork W3119886052 @default.
- W3003696480 hasRelatedWork W3126690668 @default.
- W3003696480 hasRelatedWork W3126844834 @default.
- W3003696480 hasRelatedWork W3127050431 @default.
- W3003696480 hasRelatedWork W3153758184 @default.