Matches in SemOpenAlex for { <https://semopenalex.org/work/W3187709298> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3187709298 abstract "With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information. However, methods for generating realistic counterfactual explanations for image classifiers are still rare. Especially in medical contexts, where relevant information often consists of textural and structural information, high-quality counterfactual images have the potential to give meaningful insights into decision processes. In this work, we present GANterfactual, an approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Additionally, we conduct a user study to evaluate our approach in an exemplary medical use case. Our results show that, in the chosen medical use-case, counterfactual explanations lead to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems that work with saliency maps, namely LIME and LRP." @default.
- W3187709298 created "2021-08-16" @default.
- W3187709298 creator A5021690848 @default.
- W3187709298 creator A5022969679 @default.
- W3187709298 creator A5043580137 @default.
- W3187709298 creator A5056684559 @default.
- W3187709298 creator A5063430008 @default.
- W3187709298 date "2022-04-08" @default.
- W3187709298 modified "2023-10-09" @default.
- W3187709298 title "GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning" @default.
- W3187709298 cites W1787224781 @default.
- W3187709298 cites W2127339196 @default.
- W3187709298 cites W2142225512 @default.
- W3187709298 cites W2282821441 @default.
- W3187709298 cites W2508043037 @default.
- W3187709298 cites W2618530766 @default.
- W3187709298 cites W2786513456 @default.
- W3187709298 cites W2884261459 @default.
- W3187709298 cites W2912771644 @default.
- W3187709298 cites W2951134183 @default.
- W3187709298 cites W2963095307 @default.
- W3187709298 cites W2963125461 @default.
- W3187709298 cites W2963287333 @default.
- W3187709298 cites W2971538581 @default.
- W3187709298 cites W2973136764 @default.
- W3187709298 cites W2981731882 @default.
- W3187709298 cites W2988126267 @default.
- W3187709298 cites W2994898777 @default.
- W3187709298 cites W2995406462 @default.
- W3187709298 cites W2997428643 @default.
- W3187709298 cites W3010300896 @default.
- W3187709298 cites W3099661382 @default.
- W3187709298 cites W3112492866 @default.
- W3187709298 cites W3189365070 @default.
- W3187709298 cites W3200683219 @default.
- W3187709298 cites W3202810143 @default.
- W3187709298 cites W4299627282 @default.
- W3187709298 doi "https://doi.org/10.3389/frai.2022.825565" @default.
- W3187709298 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35464995" @default.
- W3187709298 hasPublicationYear "2022" @default.
- W3187709298 type Work @default.
- W3187709298 sameAs 3187709298 @default.
- W3187709298 citedByCount "10" @default.
- W3187709298 countsByYear W31877092982022 @default.
- W3187709298 countsByYear W31877092982023 @default.
- W3187709298 crossrefType "journal-article" @default.
- W3187709298 hasAuthorship W3187709298A5021690848 @default.
- W3187709298 hasAuthorship W3187709298A5022969679 @default.
- W3187709298 hasAuthorship W3187709298A5043580137 @default.
- W3187709298 hasAuthorship W3187709298A5056684559 @default.
- W3187709298 hasAuthorship W3187709298A5063430008 @default.
- W3187709298 hasBestOaLocation W31877092981 @default.
- W3187709298 hasConcept C108650721 @default.
- W3187709298 hasConcept C119857082 @default.
- W3187709298 hasConcept C154945302 @default.
- W3187709298 hasConcept C15744967 @default.
- W3187709298 hasConcept C2522767166 @default.
- W3187709298 hasConcept C39890363 @default.
- W3187709298 hasConcept C41008148 @default.
- W3187709298 hasConcept C77805123 @default.
- W3187709298 hasConcept C95623464 @default.
- W3187709298 hasConceptScore W3187709298C108650721 @default.
- W3187709298 hasConceptScore W3187709298C119857082 @default.
- W3187709298 hasConceptScore W3187709298C154945302 @default.
- W3187709298 hasConceptScore W3187709298C15744967 @default.
- W3187709298 hasConceptScore W3187709298C2522767166 @default.
- W3187709298 hasConceptScore W3187709298C39890363 @default.
- W3187709298 hasConceptScore W3187709298C41008148 @default.
- W3187709298 hasConceptScore W3187709298C77805123 @default.
- W3187709298 hasConceptScore W3187709298C95623464 @default.
- W3187709298 hasFunder F4320320879 @default.
- W3187709298 hasFunder F4320323237 @default.
- W3187709298 hasLocation W31877092981 @default.
- W3187709298 hasLocation W31877092982 @default.
- W3187709298 hasLocation W31877092983 @default.
- W3187709298 hasLocation W31877092984 @default.
- W3187709298 hasLocation W31877092985 @default.
- W3187709298 hasOpenAccess W3187709298 @default.
- W3187709298 hasPrimaryLocation W31877092981 @default.
- W3187709298 hasRelatedWork W1576360539 @default.
- W3187709298 hasRelatedWork W2556319748 @default.
- W3187709298 hasRelatedWork W2950113871 @default.
- W3187709298 hasRelatedWork W2961085424 @default.
- W3187709298 hasRelatedWork W3092365268 @default.
- W3187709298 hasRelatedWork W4281386250 @default.
- W3187709298 hasRelatedWork W4282813524 @default.
- W3187709298 hasRelatedWork W4286629047 @default.
- W3187709298 hasRelatedWork W4306674287 @default.
- W3187709298 hasRelatedWork W4224009465 @default.
- W3187709298 hasVolume "5" @default.
- W3187709298 isParatext "false" @default.
- W3187709298 isRetracted "false" @default.
- W3187709298 magId "3187709298" @default.
- W3187709298 workType "article" @default.