Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation

Möller T (2024)
Bielefeld: Universität Bielefeld.

Bielefelder E-Dissertation | Englisch
 
Download
OA 72.68 MB
Gutachter*in / Betreuer*in
Abstract / Bemerkung
This thesis explores methods in machine learning and computer vision to extract meaningful semantic information from images, with a primary focus on marine images, while addressing challenges associated with limited prior knowledge and annotation constraints. Traditional deep learning approaches in computer vision—such as image classification, object detection, and semantic segmentation—have achieved impressive results but depend heavily on large datasets of labeled images and predefined class information. However, marine imaging often lacks these resources, as species in remote marine environments are not always known in advance, and annotated images are scarce due to limited access to trained experts. This work develops and evaluates novel techniques to address these gaps, aiming to reduce the need for domain specific labeled training data and the effort required to obtain it.
Jahr
2024
Seite(n)
195
Page URI
https://pub.uni-bielefeld.de/record/2994291

Zitieren

Möller T. Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Bielefeld: Universität Bielefeld; 2024.
Möller, T. (2024). Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Bielefeld: Universität Bielefeld. https://doi.org/10.4119/unibi/2994291
Möller, Torben. 2024. Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Bielefeld: Universität Bielefeld.
Möller, T. (2024). Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Bielefeld: Universität Bielefeld.
Möller, T., 2024. Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation, Bielefeld: Universität Bielefeld.
T. Möller, Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation, Bielefeld: Universität Bielefeld, 2024.
Möller, T.: Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Universität Bielefeld, Bielefeld (2024).
Möller, Torben. Computer vision with limited domain knowledge and annotations. Reducing domain expert effort from image acquisition to interpretation. Bielefeld: Universität Bielefeld, 2024.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International (CC BY-NC-ND 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2024-11-14T21:01:42Z
MD5 Prüfsumme
b209b39aade61062ca0b72d9bc2ebbb5


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar