Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897074540> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2897074540 abstract "The superior performance of deep convolutional networks over high-dimensional problems have made them very popular for several applications. Despite their wide adoption, their underlying mechanisms still remain unclear with their improvement procedures still relying mainly on a trial and error process. We introduce a novel sensitivity analysis based on the Gestalt theory for giving insights into the classifier function and intermediate layers. Since Gestalt psychology stipulates that perception can be a product of complex interactions among several elements, we perform an ablation study based on this concept to discover which principles and image context significantly contribute in the network classification. Our results reveal that ConvNets follow most of the visual cortical perceptual mechanisms defined by the Gestalt principles at several levels. The proposed framework stimulates specific feature maps in classification problems and reveal important network attributes that can produce more explainable network models." @default.
- W2897074540 created "2018-10-26" @default.
- W2897074540 creator A5006130495 @default.
- W2897074540 creator A5069693309 @default.
- W2897074540 creator A5071596476 @default.
- W2897074540 date "2018-10-19" @default.
- W2897074540 modified "2023-09-27" @default.
- W2897074540 title "Understanding Deep Convolutional Networks through Gestalt Theory" @default.
- W2897074540 cites W1849277567 @default.
- W2897074540 cites W1915485278 @default.
- W2897074540 cites W1932198206 @default.
- W2897074540 cites W1983428447 @default.
- W2897074540 cites W2017537431 @default.
- W2897074540 cites W2060565253 @default.
- W2897074540 cites W2097117768 @default.
- W2897074540 cites W2108598243 @default.
- W2897074540 cites W2115579991 @default.
- W2897074540 cites W2125728075 @default.
- W2897074540 cites W2133243643 @default.
- W2897074540 cites W2135276714 @default.
- W2897074540 cites W2155980216 @default.
- W2897074540 cites W2162175980 @default.
- W2897074540 cites W2412782625 @default.
- W2897074540 cites W2786178913 @default.
- W2897074540 hasPublicationYear "2018" @default.
- W2897074540 type Work @default.
- W2897074540 sameAs 2897074540 @default.
- W2897074540 citedByCount "0" @default.
- W2897074540 crossrefType "posted-content" @default.
- W2897074540 hasAuthorship W2897074540A5006130495 @default.
- W2897074540 hasAuthorship W2897074540A5069693309 @default.
- W2897074540 hasAuthorship W2897074540A5071596476 @default.
- W2897074540 hasConcept C119857082 @default.
- W2897074540 hasConcept C153180895 @default.
- W2897074540 hasConcept C154945302 @default.
- W2897074540 hasConcept C15744967 @default.
- W2897074540 hasConcept C169760540 @default.
- W2897074540 hasConcept C26760741 @default.
- W2897074540 hasConcept C27362006 @default.
- W2897074540 hasConcept C41008148 @default.
- W2897074540 hasConcept C80444323 @default.
- W2897074540 hasConcept C81363708 @default.
- W2897074540 hasConcept C95623464 @default.
- W2897074540 hasConceptScore W2897074540C119857082 @default.
- W2897074540 hasConceptScore W2897074540C153180895 @default.
- W2897074540 hasConceptScore W2897074540C154945302 @default.
- W2897074540 hasConceptScore W2897074540C15744967 @default.
- W2897074540 hasConceptScore W2897074540C169760540 @default.
- W2897074540 hasConceptScore W2897074540C26760741 @default.
- W2897074540 hasConceptScore W2897074540C27362006 @default.
- W2897074540 hasConceptScore W2897074540C41008148 @default.
- W2897074540 hasConceptScore W2897074540C80444323 @default.
- W2897074540 hasConceptScore W2897074540C81363708 @default.
- W2897074540 hasConceptScore W2897074540C95623464 @default.
- W2897074540 hasLocation W28970745401 @default.
- W2897074540 hasOpenAccess W2897074540 @default.
- W2897074540 hasPrimaryLocation W28970745401 @default.
- W2897074540 hasRelatedWork W177872859 @default.
- W2897074540 hasRelatedWork W2492109573 @default.
- W2897074540 hasRelatedWork W2519123074 @default.
- W2897074540 hasRelatedWork W2621975776 @default.
- W2897074540 hasRelatedWork W2804468818 @default.
- W2897074540 hasRelatedWork W2920450151 @default.
- W2897074540 hasRelatedWork W2923677086 @default.
- W2897074540 hasRelatedWork W2949225548 @default.
- W2897074540 hasRelatedWork W2962779158 @default.
- W2897074540 hasRelatedWork W2962783329 @default.
- W2897074540 hasRelatedWork W2962785568 @default.
- W2897074540 hasRelatedWork W2968726863 @default.
- W2897074540 hasRelatedWork W2970421120 @default.
- W2897074540 hasRelatedWork W3023072174 @default.
- W2897074540 hasRelatedWork W3032815891 @default.
- W2897074540 hasRelatedWork W3099425148 @default.
- W2897074540 hasRelatedWork W3133875925 @default.
- W2897074540 hasRelatedWork W3153606705 @default.
- W2897074540 hasRelatedWork W3193885319 @default.
- W2897074540 hasRelatedWork W3208352012 @default.
- W2897074540 isParatext "false" @default.
- W2897074540 isRetracted "false" @default.
- W2897074540 magId "2897074540" @default.
- W2897074540 workType "article" @default.