Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384703180> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4384703180 abstract "Explainable artificial intelligence (XAI) has gained considerable attention in recent years as it aims to help humans better understand machine learning decisions, making complex black-box systems more trustworthy. Visual explanation algorithms have been designed to generate heatmaps highlighting image regions that a deep neural network focuses on to make decisions. While convolutional neural network (CNN) models typically follow similar processing operations for feature encoding, the emergence of vision transformer (ViT) has introduced a new approach to machine vision decision-making. Therefore, an important question is which architecture provides more human-understandable explanations. This paper examines the explain-ability of deep architectures, including CNN and ViT models under different vision tasks. To this end, we first performed a subjective experiment asking humans to highlight the key visual features in images that helped them to make decisions in two different vision tasks. Next, using the human-annotated images, ground-truth heatmaps were generated that were compared against heatmaps generated by explanation methods for the deep architectures. Moreover, perturbation tests were performed for objective evaluation of the deep models' explanation heatmaps. According to the results, the explanations generated from ViT are deemed more trustworthy than those produced by other CNNs, and as the features of the input image are more dispersed, the advantage of the model becomes more evident." @default.
- W4384703180 created "2023-07-20" @default.
- W4384703180 creator A5034083500 @default.
- W4384703180 creator A5043511500 @default.
- W4384703180 creator A5050042610 @default.
- W4384703180 creator A5064520759 @default.
- W4384703180 date "2023-06-20" @default.
- W4384703180 modified "2023-09-30" @default.
- W4384703180 title "Evaluating Quality of Visual Explanations of Deep Learning Models for Vision Tasks" @default.
- W4384703180 cites W1787224781 @default.
- W4384703180 cites W2194775991 @default.
- W4384703180 cites W2195388612 @default.
- W4384703180 cites W2240067561 @default.
- W4384703180 cites W2766207481 @default.
- W4384703180 cites W2952487041 @default.
- W4384703180 cites W2962770929 @default.
- W4384703180 cites W2962858109 @default.
- W4384703180 cites W2963503775 @default.
- W4384703180 cites W2988157455 @default.
- W4384703180 cites W3000716014 @default.
- W4384703180 cites W3034175346 @default.
- W4384703180 cites W3035422918 @default.
- W4384703180 cites W3035916825 @default.
- W4384703180 cites W3138516171 @default.
- W4384703180 cites W3176196997 @default.
- W4384703180 cites W4286218466 @default.
- W4384703180 cites W4312407344 @default.
- W4384703180 cites W4312443924 @default.
- W4384703180 doi "https://doi.org/10.1109/qomex58391.2023.10178510" @default.
- W4384703180 hasPublicationYear "2023" @default.
- W4384703180 type Work @default.
- W4384703180 citedByCount "0" @default.
- W4384703180 crossrefType "proceedings-article" @default.
- W4384703180 hasAuthorship W4384703180A5034083500 @default.
- W4384703180 hasAuthorship W4384703180A5043511500 @default.
- W4384703180 hasAuthorship W4384703180A5050042610 @default.
- W4384703180 hasAuthorship W4384703180A5064520759 @default.
- W4384703180 hasConcept C108583219 @default.
- W4384703180 hasConcept C115961682 @default.
- W4384703180 hasConcept C119857082 @default.
- W4384703180 hasConcept C146849305 @default.
- W4384703180 hasConcept C153701036 @default.
- W4384703180 hasConcept C154945302 @default.
- W4384703180 hasConcept C160086991 @default.
- W4384703180 hasConcept C2984842247 @default.
- W4384703180 hasConcept C38652104 @default.
- W4384703180 hasConcept C41008148 @default.
- W4384703180 hasConcept C50644808 @default.
- W4384703180 hasConcept C81363708 @default.
- W4384703180 hasConceptScore W4384703180C108583219 @default.
- W4384703180 hasConceptScore W4384703180C115961682 @default.
- W4384703180 hasConceptScore W4384703180C119857082 @default.
- W4384703180 hasConceptScore W4384703180C146849305 @default.
- W4384703180 hasConceptScore W4384703180C153701036 @default.
- W4384703180 hasConceptScore W4384703180C154945302 @default.
- W4384703180 hasConceptScore W4384703180C160086991 @default.
- W4384703180 hasConceptScore W4384703180C2984842247 @default.
- W4384703180 hasConceptScore W4384703180C38652104 @default.
- W4384703180 hasConceptScore W4384703180C41008148 @default.
- W4384703180 hasConceptScore W4384703180C50644808 @default.
- W4384703180 hasConceptScore W4384703180C81363708 @default.
- W4384703180 hasLocation W43847031801 @default.
- W4384703180 hasOpenAccess W4384703180 @default.
- W4384703180 hasPrimaryLocation W43847031801 @default.
- W4384703180 hasRelatedWork W2279398222 @default.
- W4384703180 hasRelatedWork W2337926734 @default.
- W4384703180 hasRelatedWork W2915754718 @default.
- W4384703180 hasRelatedWork W3021430260 @default.
- W4384703180 hasRelatedWork W3133861977 @default.
- W4384703180 hasRelatedWork W3136076031 @default.
- W4384703180 hasRelatedWork W4299822940 @default.
- W4384703180 hasRelatedWork W4321369474 @default.
- W4384703180 hasRelatedWork W4366224123 @default.
- W4384703180 hasRelatedWork W4381487685 @default.
- W4384703180 isParatext "false" @default.
- W4384703180 isRetracted "false" @default.
- W4384703180 workType "article" @default.