Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384157099> ?p ?o ?g. }
- W4384157099 endingPage "103782" @default.
- W4384157099 startingPage "103782" @default.
- W4384157099 abstract "Deep neural networks have shown their profound impact on achieving human-level performance in visual saliency prediction. However, it is still unclear how they learn their task and what it means in terms of understanding human visual system. In this work, we propose a framework to derive explainable saliency models from their corresponding deep architectures. Mainly, we explain a deep saliency model by understanding its four different aspects: (1) intermediate activation maps of deep layers, (2) biologically plausible Log-Gabor (LG) filters for salient region identification, (3) positional biased behavior of Log-Gabor filters and (4) processing of color information by establishing a relevance with human visual system. We consider four state-of-the-art (SOTA) deep saliency models, namely CMRNet, UNISAL, DeepGaze IIE, and MSI-Net for their interpretation using our proposed framework. We observe that explainable models perform way better than the classical SOTA models. We also find that CMRNet transforms the input RGB space to a representation after the input layer, which is very close to YUV space of a color image. Then, we discuss about the biological consideration and relevance of our framework for its possible anatomical substratum of visual attention. We find a good correlation between components of HVS and the base operations of the proposed technique. Hence, we say that this generic explainable framework provides a new perspective to see relationship between classical methods/human visual system and DNN based ones." @default.
- W4384157099 created "2023-07-14" @default.
- W4384157099 creator A5024090300 @default.
- W4384157099 creator A5037492743 @default.
- W4384157099 creator A5086242686 @default.
- W4384157099 creator A5091195976 @default.
- W4384157099 date "2023-10-01" @default.
- W4384157099 modified "2023-10-18" @default.
- W4384157099 title "Towards explainable deep visual saliency models" @default.
- W4384157099 cites W1526492552 @default.
- W4384157099 cites W1982447763 @default.
- W4384157099 cites W1992480897 @default.
- W4384157099 cites W1994202260 @default.
- W4384157099 cites W2007226897 @default.
- W4384157099 cites W2008066834 @default.
- W4384157099 cites W2030522750 @default.
- W4384157099 cites W2037499916 @default.
- W4384157099 cites W2066462711 @default.
- W4384157099 cites W2069912449 @default.
- W4384157099 cites W2071555787 @default.
- W4384157099 cites W2128272608 @default.
- W4384157099 cites W2133665775 @default.
- W4384157099 cites W2145889472 @default.
- W4384157099 cites W2149095485 @default.
- W4384157099 cites W2150052800 @default.
- W4384157099 cites W2152233525 @default.
- W4384157099 cites W2162725331 @default.
- W4384157099 cites W2378845821 @default.
- W4384157099 cites W2397603165 @default.
- W4384157099 cites W2605067324 @default.
- W4384157099 cites W2732026016 @default.
- W4384157099 cites W2883476439 @default.
- W4384157099 cites W2891503716 @default.
- W4384157099 cites W2902499998 @default.
- W4384157099 cites W2952237357 @default.
- W4384157099 cites W2962772482 @default.
- W4384157099 cites W3004895274 @default.
- W4384157099 cites W3022565501 @default.
- W4384157099 cites W3101840568 @default.
- W4384157099 cites W4254735300 @default.
- W4384157099 doi "https://doi.org/10.1016/j.cviu.2023.103782" @default.
- W4384157099 hasPublicationYear "2023" @default.
- W4384157099 type Work @default.
- W4384157099 citedByCount "0" @default.
- W4384157099 crossrefType "journal-article" @default.
- W4384157099 hasAuthorship W4384157099A5024090300 @default.
- W4384157099 hasAuthorship W4384157099A5037492743 @default.
- W4384157099 hasAuthorship W4384157099A5086242686 @default.
- W4384157099 hasAuthorship W4384157099A5091195976 @default.
- W4384157099 hasConcept C108583219 @default.
- W4384157099 hasConcept C115961682 @default.
- W4384157099 hasConcept C12713177 @default.
- W4384157099 hasConcept C153180895 @default.
- W4384157099 hasConcept C154945302 @default.
- W4384157099 hasConcept C158154518 @default.
- W4384157099 hasConcept C160086991 @default.
- W4384157099 hasConcept C17744445 @default.
- W4384157099 hasConcept C199539241 @default.
- W4384157099 hasConcept C2776359362 @default.
- W4384157099 hasConcept C2780719617 @default.
- W4384157099 hasConcept C2984842247 @default.
- W4384157099 hasConcept C31972630 @default.
- W4384157099 hasConcept C41008148 @default.
- W4384157099 hasConcept C82990744 @default.
- W4384157099 hasConcept C94625758 @default.
- W4384157099 hasConceptScore W4384157099C108583219 @default.
- W4384157099 hasConceptScore W4384157099C115961682 @default.
- W4384157099 hasConceptScore W4384157099C12713177 @default.
- W4384157099 hasConceptScore W4384157099C153180895 @default.
- W4384157099 hasConceptScore W4384157099C154945302 @default.
- W4384157099 hasConceptScore W4384157099C158154518 @default.
- W4384157099 hasConceptScore W4384157099C160086991 @default.
- W4384157099 hasConceptScore W4384157099C17744445 @default.
- W4384157099 hasConceptScore W4384157099C199539241 @default.
- W4384157099 hasConceptScore W4384157099C2776359362 @default.
- W4384157099 hasConceptScore W4384157099C2780719617 @default.
- W4384157099 hasConceptScore W4384157099C2984842247 @default.
- W4384157099 hasConceptScore W4384157099C31972630 @default.
- W4384157099 hasConceptScore W4384157099C41008148 @default.
- W4384157099 hasConceptScore W4384157099C82990744 @default.
- W4384157099 hasConceptScore W4384157099C94625758 @default.
- W4384157099 hasFunder F4320325536 @default.
- W4384157099 hasLocation W43841570991 @default.
- W4384157099 hasOpenAccess W4384157099 @default.
- W4384157099 hasPrimaryLocation W43841570991 @default.
- W4384157099 hasRelatedWork W2052518016 @default.
- W4384157099 hasRelatedWork W2081022503 @default.
- W4384157099 hasRelatedWork W2085956791 @default.
- W4384157099 hasRelatedWork W2283162247 @default.
- W4384157099 hasRelatedWork W2314488738 @default.
- W4384157099 hasRelatedWork W2524507886 @default.
- W4384157099 hasRelatedWork W2767823485 @default.
- W4384157099 hasRelatedWork W2771653066 @default.
- W4384157099 hasRelatedWork W2901949253 @default.
- W4384157099 hasRelatedWork W4212983513 @default.
- W4384157099 hasVolume "235" @default.
- W4384157099 isParatext "false" @default.
- W4384157099 isRetracted "false" @default.