Interactive Attribution-based Explanations for Image Segmentation

Simple item page
dc.contributor.authorHumer, Christinaen_US
dc.contributor.authorElharty, Mohameden_US
dc.contributor.authorHinterreiter, Andreasen_US
dc.contributor.authorStreit, Marcen_US
dc.contributor.editorKrone, Michaelen_US
dc.contributor.editorLenti, Simoneen_US
dc.contributor.editorSchmidt, Johannaen_US
dc.date.accessioned2022-06-02T15:29:18Z
dc.date.available2022-06-02T15:29:18Z
dc.date.issued2022
dc.description.abstractExplanations of deep neural networks (DNNs) give users a better understanding of the inner workings and generalizability of a network. While the majority of research focuses on explanations for classification networks, in this work we focus on explainability for image segmentation networks. As a first contribution, we introduce a lightweight framework that allows generalizing certain attribution-based explanations, originally developed for classification networks, to also work for segmentation networks. The second contribution is a web-based tool that utilizes this framework and allows users to interactively explore segmentation networks. We demonstrate the approach using a self-trained mushroom segmentation network.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEuroVis 2022 - Posters
dc.identifier.doi10.2312/evp.20221130
dc.identifier.isbn978-3-03868-185-4
dc.identifier.pages99-101
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/evp.20221130
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evp20221130
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing --> Visual analytics; Computing methodologies --> Image segmentation
dc.subjectHuman centered computing
dc.subjectVisual analytics
dc.subjectComputing methodologies
dc.subjectImage segmentation
dc.titleInteractive Attribution-based Explanations for Image Segmentationen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
099-101.pdf
Size:
360.74 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
4860-file1.pdf
Size:
1.11 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVisPosters2022