Learning on image data
Contact person: Anne H. Schistad Solberg
Keywords: Self-supervised learning, interpretable and explainable models, uncertainty estimation
Research group: Digital Signal Processing and Image Analysis (DSB)
Department of Informatics
When working with advanced images from medical imaging, earth observation, monitoring the marine enviroment or the subsurface of the earth, the next generation deep learning algorithms that can handle limited labelled data, incorporate prior knowledge or physical/geometrical constraint, and provide reliable and interpretable predictions, including uncertainty estimates are needed. We are looking for project descriptions relevant to or Center Visual Intelligence https://visual-intelligence.nowww.visual-intelligence.no.
Methodological research topics:
- Self-supervised learning
- Interpretable and explainable models
- Models incorporating physical, anatomical, or geometrical constraint.
- Models including uncertainty estimation
We have close collaboration with Norwegian companies like GE Healthcare, university hospitals, the Institute of Marine Research, Kongsberg Satellite Services, and Equinor. Access to real-world datasets and challenging real problems give large opportunities for new research of significant impact to the domains.
Mentoring and internship will be offered by a relevant external partner.