Matches in SemOpenAlex for { <https://semopenalex.org/work/W3142164242> ?p ?o ?g. }
- W3142164242 abstract "In recent years, deep learning has become prevalent to solve applications from multiple domains. Convolutional Neural Networks (CNNs) particularly have demonstrated state of the art performance for the task of image classification. However, the decisions made by these networks are not transparent and cannot be directly interpreted by a human. Several approaches have been proposed to explain to understand the reasoning behind a prediction made by a network. In this paper, we propose a topology of grouping these methods based on their assumptions and implementations. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision. Given the task of image classification and a trained CNN, this work aims to provide a comprehensive and detailed overview of a set of methods that can be used to create explanation maps for a particular image, that assign an importance score to each pixel of the image based on its contribution to the decision of the network. We also propose a further classification of the white box methods based on their implementations to enable better comparisons and help researchers find methods best suited for different scenarios." @default.
- W3142164242 created "2021-04-13" @default.
- W3142164242 creator A5041678611 @default.
- W3142164242 creator A5084035589 @default.
- W3142164242 creator A5089758511 @default.
- W3142164242 date "2021-04-06" @default.
- W3142164242 modified "2023-09-27" @default.
- W3142164242 title "White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks" @default.
- W3142164242 cites W1787224781 @default.
- W3142164242 cites W1849277567 @default.
- W3142164242 cites W2027857686 @default.
- W3142164242 cites W2099471712 @default.
- W3142164242 cites W2108598243 @default.
- W3142164242 cites W2120284346 @default.
- W3142164242 cites W2149933564 @default.
- W3142164242 cites W2163922914 @default.
- W3142164242 cites W2195388612 @default.
- W3142164242 cites W2240067561 @default.
- W3142164242 cites W2243397390 @default.
- W3142164242 cites W2282821441 @default.
- W3142164242 cites W2295107390 @default.
- W3142164242 cites W2518728805 @default.
- W3142164242 cites W2591954064 @default.
- W3142164242 cites W2594633041 @default.
- W3142164242 cites W2603519109 @default.
- W3142164242 cites W2605409611 @default.
- W3142164242 cites W2626639386 @default.
- W3142164242 cites W2769421449 @default.
- W3142164242 cites W2891612330 @default.
- W3142164242 cites W2909417901 @default.
- W3142164242 cites W2962772482 @default.
- W3142164242 cites W2962835968 @default.
- W3142164242 cites W2962851944 @default.
- W3142164242 cites W2962858109 @default.
- W3142164242 cites W2963207607 @default.
- W3142164242 cites W2963249138 @default.
- W3142164242 cites W2963382180 @default.
- W3142164242 cites W2963420686 @default.
- W3142164242 cites W2963503775 @default.
- W3142164242 cites W2964153729 @default.
- W3142164242 cites W2964285471 @default.
- W3142164242 cites W2970621010 @default.
- W3142164242 cites W2972978833 @default.
- W3142164242 cites W2980030301 @default.
- W3142164242 cites W2980458406 @default.
- W3142164242 cites W3001814198 @default.
- W3142164242 cites W3016762899 @default.
- W3142164242 cites W3093212496 @default.
- W3142164242 cites W3094574213 @default.
- W3142164242 cites W3101792976 @default.
- W3142164242 cites W3103557498 @default.
- W3142164242 cites W3106093299 @default.
- W3142164242 cites W3110730242 @default.
- W3142164242 cites W3113100858 @default.
- W3142164242 cites W3130456532 @default.
- W3142164242 cites W3135425227 @default.
- W3142164242 cites W3136862623 @default.
- W3142164242 cites W3156228749 @default.
- W3142164242 cites W3194590513 @default.
- W3142164242 hasPublicationYear "2021" @default.
- W3142164242 type Work @default.
- W3142164242 sameAs 3142164242 @default.
- W3142164242 citedByCount "0" @default.
- W3142164242 crossrefType "posted-content" @default.
- W3142164242 hasAuthorship W3142164242A5041678611 @default.
- W3142164242 hasAuthorship W3142164242A5084035589 @default.
- W3142164242 hasAuthorship W3142164242A5089758511 @default.
- W3142164242 hasConcept C108583219 @default.
- W3142164242 hasConcept C115961682 @default.
- W3142164242 hasConcept C119857082 @default.
- W3142164242 hasConcept C153083717 @default.
- W3142164242 hasConcept C153180895 @default.
- W3142164242 hasConcept C154945302 @default.
- W3142164242 hasConcept C160633673 @default.
- W3142164242 hasConcept C162324750 @default.
- W3142164242 hasConcept C177264268 @default.
- W3142164242 hasConcept C180932941 @default.
- W3142164242 hasConcept C187736073 @default.
- W3142164242 hasConcept C199360897 @default.
- W3142164242 hasConcept C26713055 @default.
- W3142164242 hasConcept C2780451532 @default.
- W3142164242 hasConcept C41008148 @default.
- W3142164242 hasConcept C50644808 @default.
- W3142164242 hasConcept C75294576 @default.
- W3142164242 hasConcept C81363708 @default.
- W3142164242 hasConcept C94966114 @default.
- W3142164242 hasConceptScore W3142164242C108583219 @default.
- W3142164242 hasConceptScore W3142164242C115961682 @default.
- W3142164242 hasConceptScore W3142164242C119857082 @default.
- W3142164242 hasConceptScore W3142164242C153083717 @default.
- W3142164242 hasConceptScore W3142164242C153180895 @default.
- W3142164242 hasConceptScore W3142164242C154945302 @default.
- W3142164242 hasConceptScore W3142164242C160633673 @default.
- W3142164242 hasConceptScore W3142164242C162324750 @default.
- W3142164242 hasConceptScore W3142164242C177264268 @default.
- W3142164242 hasConceptScore W3142164242C180932941 @default.
- W3142164242 hasConceptScore W3142164242C187736073 @default.
- W3142164242 hasConceptScore W3142164242C199360897 @default.
- W3142164242 hasConceptScore W3142164242C26713055 @default.
- W3142164242 hasConceptScore W3142164242C2780451532 @default.