Matches in SemOpenAlex for { <https://semopenalex.org/work/W4301690967> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4301690967 abstract "We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps. Layer-wise Relevance Propagation (LRP) is a method to compute scores for individual components of an input image, denoting their contribution to the prediction of the classifier for one particular test point. We demonstrate the impact of different choices of decomposition cut-off points during the LRP-process, controlling the resolution and semantics of the heatmap on test images from the PASCAL VOC 2007 test data set." @default.
- W4301690967 created "2022-10-05" @default.
- W4301690967 creator A5026451495 @default.
- W4301690967 creator A5033420601 @default.
- W4301690967 creator A5072460783 @default.
- W4301690967 creator A5072994165 @default.
- W4301690967 date "2016-03-21" @default.
- W4301690967 modified "2023-09-27" @default.
- W4301690967 title "Controlling Explanatory Heatmap Resolution and Semantics via Decomposition Depth" @default.
- W4301690967 doi "https://doi.org/10.48550/arxiv.1603.06463" @default.
- W4301690967 hasPublicationYear "2016" @default.
- W4301690967 type Work @default.
- W4301690967 citedByCount "0" @default.
- W4301690967 crossrefType "posted-content" @default.
- W4301690967 hasAuthorship W4301690967A5026451495 @default.
- W4301690967 hasAuthorship W4301690967A5033420601 @default.
- W4301690967 hasAuthorship W4301690967A5072460783 @default.
- W4301690967 hasAuthorship W4301690967A5072994165 @default.
- W4301690967 hasBestOaLocation W43016909671 @default.
- W4301690967 hasConcept C11413529 @default.
- W4301690967 hasConcept C12267149 @default.
- W4301690967 hasConcept C153180895 @default.
- W4301690967 hasConcept C154945302 @default.
- W4301690967 hasConcept C169903167 @default.
- W4301690967 hasConcept C199360897 @default.
- W4301690967 hasConcept C41008148 @default.
- W4301690967 hasConcept C75608658 @default.
- W4301690967 hasConcept C81363708 @default.
- W4301690967 hasConcept C95623464 @default.
- W4301690967 hasConceptScore W4301690967C11413529 @default.
- W4301690967 hasConceptScore W4301690967C12267149 @default.
- W4301690967 hasConceptScore W4301690967C153180895 @default.
- W4301690967 hasConceptScore W4301690967C154945302 @default.
- W4301690967 hasConceptScore W4301690967C169903167 @default.
- W4301690967 hasConceptScore W4301690967C199360897 @default.
- W4301690967 hasConceptScore W4301690967C41008148 @default.
- W4301690967 hasConceptScore W4301690967C75608658 @default.
- W4301690967 hasConceptScore W4301690967C81363708 @default.
- W4301690967 hasConceptScore W4301690967C95623464 @default.
- W4301690967 hasLocation W43016909671 @default.
- W4301690967 hasLocation W43016909672 @default.
- W4301690967 hasOpenAccess W4301690967 @default.
- W4301690967 hasPrimaryLocation W43016909671 @default.
- W4301690967 hasRelatedWork W2041399278 @default.
- W4301690967 hasRelatedWork W2136184105 @default.
- W4301690967 hasRelatedWork W2336974148 @default.
- W4301690967 hasRelatedWork W2424871898 @default.
- W4301690967 hasRelatedWork W2996933976 @default.
- W4301690967 hasRelatedWork W3013515612 @default.
- W4301690967 hasRelatedWork W3208266890 @default.
- W4301690967 hasRelatedWork W4225852842 @default.
- W4301690967 hasRelatedWork W2187500075 @default.
- W4301690967 hasRelatedWork W2345184372 @default.
- W4301690967 isParatext "false" @default.
- W4301690967 isRetracted "false" @default.
- W4301690967 workType "article" @default.