Versenden
Drucken
Karmakar, Chandrabali und Pogorzelski, David und Arlinghaus, Peter und Camero, Andres und Zhang, Wenyan (2024) Trustworthy Unsupervised ML Model for Drawing Coastlines and Creating Benchmark Dataset. Helmholtz Imaging Annual Conference 2024, 2024-05-14 - 2024-05-15, Heidelberg.
![[img]](https://elib.dlr.de/style/images/fileicons/application_pdf.png) |
PDF
4MB |
Kurzfassung
The research focuses in use of trustworthy AI models in remote sensing image segmentation. An unsupervosed model with uncertainty quantification capabilities has been used to label images. the model helps reducing labelling effirt by tactful use of uncertainty score. A visual tool is also developed to support the work.
| elib-URL des Eintrags: | https://elib.dlr.de/208589/ | ||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dokumentart: | Konferenzbeitrag (Vorlesung) | ||||||||||||||||||||||||
| Titel: | Trustworthy Unsupervised ML Model for Drawing Coastlines and Creating Benchmark Dataset | ||||||||||||||||||||||||
| Autoren: |
| ||||||||||||||||||||||||
| Datum: | 15 Mai 2024 | ||||||||||||||||||||||||
| Referierte Publikation: | Nein | ||||||||||||||||||||||||
| Open Access: | Ja | ||||||||||||||||||||||||
| Gold Open Access: | Nein | ||||||||||||||||||||||||
| In SCOPUS: | Nein | ||||||||||||||||||||||||
| In ISI Web of Science: | Nein | ||||||||||||||||||||||||
| Status: | veröffentlicht | ||||||||||||||||||||||||
| Stichwörter: | Trustworthy AI, Unsupervised model, Uncertainty quantification | ||||||||||||||||||||||||
| Veranstaltungstitel: | Helmholtz Imaging Annual Conference 2024 | ||||||||||||||||||||||||
| Veranstaltungsort: | Heidelberg | ||||||||||||||||||||||||
| Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||||||
| Veranstaltungsbeginn: | 14 Mai 2024 | ||||||||||||||||||||||||
| Veranstaltungsende: | 15 Mai 2024 | ||||||||||||||||||||||||
| Veranstalter : | Helmholtz Association | ||||||||||||||||||||||||
| HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||||||
| HGF - Programm: | Raumfahrt | ||||||||||||||||||||||||
| HGF - Programmthema: | Erdbeobachtung | ||||||||||||||||||||||||
| DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||||||||||
| DLR - Forschungsgebiet: | R EO - Erdbeobachtung | ||||||||||||||||||||||||
| DLR - Teilgebiet (Projekt, Vorhaben): | R - Künstliche Intelligenz | ||||||||||||||||||||||||
| Standort: | Oberpfaffenhofen | ||||||||||||||||||||||||
| Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > EO Data Science | ||||||||||||||||||||||||
| Hinterlegt von: | Karmakar, Chandrabali | ||||||||||||||||||||||||
| Hinterlegt am: | 14 Nov 2024 13:58 | ||||||||||||||||||||||||
| Letzte Änderung: | 14 Nov 2024 13:58 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags
