Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283267930> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4283267930 endingPage "109287" @default.
- W4283267930 startingPage "109287" @default.
- W4283267930 abstract "There is an increasing demand to understand how neural networks make decisions when classifying images. Recent deep learning models have a black box architecture that limits the ability to explore their functionality. This paper presents an explainable method called Augmented Score-CAM, built on top of the existing Score-CAM and the existing image augmentation techniques. Unlike previous methods that relied on one input image to generate class activation maps, we adopt the image augmentation technique used to train convolutional neural networks. We use the input image to create a set of augmented images and generate a class activation map for each. The final activation map is obtained by combining augmented activation maps. We evaluate the model by performing qualitative and quantitative experiments. Augmented Score-CAM outperformed Score-CAM in terms of human trust, faithfulness, and object localization. Our model passed the sanity check and was found to be sensitive to network and dataset randomization. Moreover, we proposed the use of feature space augmentations by embedding neural style transfer in the model." @default.
- W4283267930 created "2022-06-23" @default.
- W4283267930 creator A5026547820 @default.
- W4283267930 creator A5087753797 @default.
- W4283267930 date "2022-09-01" @default.
- W4283267930 modified "2023-10-11" @default.
- W4283267930 title "Augmented Score-CAM: High resolution visual interpretations for deep neural networks" @default.
- W4283267930 cites W2048231652 @default.
- W4283267930 cites W2061939373 @default.
- W4283267930 cites W2125847307 @default.
- W4283267930 cites W2171583938 @default.
- W4283267930 cites W2194775991 @default.
- W4283267930 cites W2282821441 @default.
- W4283267930 cites W2295107390 @default.
- W4283267930 cites W2522925973 @default.
- W4283267930 cites W2618530766 @default.
- W4283267930 cites W2666919929 @default.
- W4283267930 cites W2800017313 @default.
- W4283267930 cites W2889404246 @default.
- W4283267930 cites W2910705748 @default.
- W4283267930 cites W2931000849 @default.
- W4283267930 cites W2934533499 @default.
- W4283267930 cites W2937343562 @default.
- W4283267930 cites W2954996726 @default.
- W4283267930 cites W2963920537 @default.
- W4283267930 cites W2981731882 @default.
- W4283267930 cites W2994898777 @default.
- W4283267930 cites W3035253074 @default.
- W4283267930 cites W3102564565 @default.
- W4283267930 cites W3180293735 @default.
- W4283267930 doi "https://doi.org/10.1016/j.knosys.2022.109287" @default.
- W4283267930 hasPublicationYear "2022" @default.
- W4283267930 type Work @default.
- W4283267930 citedByCount "6" @default.
- W4283267930 countsByYear W42832679302023 @default.
- W4283267930 crossrefType "journal-article" @default.
- W4283267930 hasAuthorship W4283267930A5026547820 @default.
- W4283267930 hasAuthorship W4283267930A5087753797 @default.
- W4283267930 hasConcept C119857082 @default.
- W4283267930 hasConcept C138268822 @default.
- W4283267930 hasConcept C154945302 @default.
- W4283267930 hasConcept C2984842247 @default.
- W4283267930 hasConcept C31972630 @default.
- W4283267930 hasConcept C41008148 @default.
- W4283267930 hasConcept C50644808 @default.
- W4283267930 hasConceptScore W4283267930C119857082 @default.
- W4283267930 hasConceptScore W4283267930C138268822 @default.
- W4283267930 hasConceptScore W4283267930C154945302 @default.
- W4283267930 hasConceptScore W4283267930C2984842247 @default.
- W4283267930 hasConceptScore W4283267930C31972630 @default.
- W4283267930 hasConceptScore W4283267930C41008148 @default.
- W4283267930 hasConceptScore W4283267930C50644808 @default.
- W4283267930 hasLocation W42832679301 @default.
- W4283267930 hasOpenAccess W4283267930 @default.
- W4283267930 hasPrimaryLocation W42832679301 @default.
- W4283267930 hasRelatedWork W1982750869 @default.
- W4283267930 hasRelatedWork W1984922432 @default.
- W4283267930 hasRelatedWork W2025517136 @default.
- W4283267930 hasRelatedWork W2028664052 @default.
- W4283267930 hasRelatedWork W2082780921 @default.
- W4283267930 hasRelatedWork W2362198218 @default.
- W4283267930 hasRelatedWork W2375008505 @default.
- W4283267930 hasRelatedWork W2391251536 @default.
- W4283267930 hasRelatedWork W2961085424 @default.
- W4283267930 hasRelatedWork W634414395 @default.
- W4283267930 hasVolume "252" @default.
- W4283267930 isParatext "false" @default.
- W4283267930 isRetracted "false" @default.
- W4283267930 workType "article" @default.