Interactive Attribution-based Explanations for Image Segmentation
| dc.contributor.author | Humer, Christina | en_US |
| dc.contributor.author | Elharty, Mohamed | en_US |
| dc.contributor.author | Hinterreiter, Andreas | en_US |
| dc.contributor.author | Streit, Marc | en_US |
| dc.contributor.editor | Krone, Michael | en_US |
| dc.contributor.editor | Lenti, Simone | en_US |
| dc.contributor.editor | Schmidt, Johanna | en_US |
| dc.date.accessioned | 2022-06-02T15:29:18Z | |
| dc.date.available | 2022-06-02T15:29:18Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Explanations 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.sectionheaders | Posters | |
| dc.description.seriesinformation | EuroVis 2022 - Posters | |
| dc.identifier.doi | 10.2312/evp.20221130 | |
| dc.identifier.isbn | 978-3-03868-185-4 | |
| dc.identifier.pages | 99-101 | |
| dc.identifier.pages | 3 pages | |
| dc.identifier.uri | https://doi.org/10.2312/evp.20221130 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/evp20221130 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Human-centered computing --> Visual analytics; Computing methodologies --> Image segmentation | |
| dc.subject | Human centered computing | |
| dc.subject | Visual analytics | |
| dc.subject | Computing methodologies | |
| dc.subject | Image segmentation | |
| dc.title | Interactive Attribution-based Explanations for Image Segmentation | en_US |