Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319878045> ?p ?o ?g. }
- W4319878045 abstract "Abstract The accuracy and flexibility of Deep Convolutional Neural Networks (DCNNs) have been highly validated over the past years. However, their intrinsic opaqueness is still affecting their reliability and limiting their application in critical production systems, where the black-box behavior is difficult to be accepted. This work proposes EBAnO , an innovative explanation framework able to analyze the decision-making process of DCNNs in image classification by providing prediction-local and class-based model-wise explanations through the unsupervised mining of knowledge contained in multiple convolutional layers. EBAnO provides detailed visual and numerical explanations thanks to two specific indexes that measure the features’ influence and their influence precision in the decision-making process. The framework has been experimentally evaluated, both quantitatively and qualitatively, by (i) analyzing its explanations with four state-of-the-art DCNN architectures, (ii) comparing its results with three state-of-the-art explanation strategies and (iii) assessing its effectiveness and easiness of understanding through human judgment, by means of an online survey. EBAnO has been released as open-source code and it is freely available online." @default.
- W4319878045 created "2023-02-11" @default.
- W4319878045 creator A5026005294 @default.
- W4319878045 creator A5053742461 @default.
- W4319878045 creator A5061608915 @default.
- W4319878045 creator A5081839375 @default.
- W4319878045 date "2023-02-10" @default.
- W4319878045 modified "2023-09-25" @default.
- W4319878045 title "Explaining deep convolutional models by measuring the influence of interpretable features in image classification" @default.
- W4319878045 cites W1787224781 @default.
- W4319878045 cites W1806716066 @default.
- W4319878045 cites W1861492603 @default.
- W4319878045 cites W1948751323 @default.
- W4319878045 cites W2117539524 @default.
- W4319878045 cites W2129888542 @default.
- W4319878045 cites W2150593711 @default.
- W4319878045 cites W2155904486 @default.
- W4319878045 cites W2163922914 @default.
- W4319878045 cites W2183341477 @default.
- W4319878045 cites W2190008860 @default.
- W4319878045 cites W2282821441 @default.
- W4319878045 cites W2295107390 @default.
- W4319878045 cites W2336525064 @default.
- W4319878045 cites W2487898712 @default.
- W4319878045 cites W2510508396 @default.
- W4319878045 cites W2613099550 @default.
- W4319878045 cites W2764024122 @default.
- W4319878045 cites W2796095619 @default.
- W4319878045 cites W2811018197 @default.
- W4319878045 cites W2889313789 @default.
- W4319878045 cites W2891503716 @default.
- W4319878045 cites W2892868562 @default.
- W4319878045 cites W2901876975 @default.
- W4319878045 cites W2943554161 @default.
- W4319878045 cites W2962700793 @default.
- W4319878045 cites W2962807820 @default.
- W4319878045 cites W2964350391 @default.
- W4319878045 cites W2969880113 @default.
- W4319878045 cites W2972441196 @default.
- W4319878045 cites W2972854536 @default.
- W4319878045 cites W2998702515 @default.
- W4319878045 cites W3005142675 @default.
- W4319878045 cites W3035836689 @default.
- W4319878045 cites W3092711134 @default.
- W4319878045 cites W3100711616 @default.
- W4319878045 cites W3101609372 @default.
- W4319878045 cites W3102564565 @default.
- W4319878045 cites W3132455321 @default.
- W4319878045 cites W4283332711 @default.
- W4319878045 doi "https://doi.org/10.1007/s10618-023-00915-x" @default.
- W4319878045 hasPublicationYear "2023" @default.
- W4319878045 type Work @default.
- W4319878045 citedByCount "0" @default.
- W4319878045 crossrefType "journal-article" @default.
- W4319878045 hasAuthorship W4319878045A5026005294 @default.
- W4319878045 hasAuthorship W4319878045A5053742461 @default.
- W4319878045 hasAuthorship W4319878045A5061608915 @default.
- W4319878045 hasAuthorship W4319878045A5081839375 @default.
- W4319878045 hasBestOaLocation W43198780451 @default.
- W4319878045 hasConcept C105795698 @default.
- W4319878045 hasConcept C108583219 @default.
- W4319878045 hasConcept C111919701 @default.
- W4319878045 hasConcept C115961682 @default.
- W4319878045 hasConcept C119857082 @default.
- W4319878045 hasConcept C121332964 @default.
- W4319878045 hasConcept C124101348 @default.
- W4319878045 hasConcept C153180895 @default.
- W4319878045 hasConcept C154945302 @default.
- W4319878045 hasConcept C163258240 @default.
- W4319878045 hasConcept C177264268 @default.
- W4319878045 hasConcept C199360897 @default.
- W4319878045 hasConcept C2776760102 @default.
- W4319878045 hasConcept C2780598303 @default.
- W4319878045 hasConcept C33923547 @default.
- W4319878045 hasConcept C41008148 @default.
- W4319878045 hasConcept C43214815 @default.
- W4319878045 hasConcept C62520636 @default.
- W4319878045 hasConcept C75294576 @default.
- W4319878045 hasConcept C81363708 @default.
- W4319878045 hasConcept C94966114 @default.
- W4319878045 hasConcept C98045186 @default.
- W4319878045 hasConceptScore W4319878045C105795698 @default.
- W4319878045 hasConceptScore W4319878045C108583219 @default.
- W4319878045 hasConceptScore W4319878045C111919701 @default.
- W4319878045 hasConceptScore W4319878045C115961682 @default.
- W4319878045 hasConceptScore W4319878045C119857082 @default.
- W4319878045 hasConceptScore W4319878045C121332964 @default.
- W4319878045 hasConceptScore W4319878045C124101348 @default.
- W4319878045 hasConceptScore W4319878045C153180895 @default.
- W4319878045 hasConceptScore W4319878045C154945302 @default.
- W4319878045 hasConceptScore W4319878045C163258240 @default.
- W4319878045 hasConceptScore W4319878045C177264268 @default.
- W4319878045 hasConceptScore W4319878045C199360897 @default.
- W4319878045 hasConceptScore W4319878045C2776760102 @default.
- W4319878045 hasConceptScore W4319878045C2780598303 @default.
- W4319878045 hasConceptScore W4319878045C33923547 @default.
- W4319878045 hasConceptScore W4319878045C41008148 @default.
- W4319878045 hasConceptScore W4319878045C43214815 @default.
- W4319878045 hasConceptScore W4319878045C62520636 @default.
- W4319878045 hasConceptScore W4319878045C75294576 @default.