Job description

I am the Director of Visual Intelligence. This is a Centre for Research-based Innovation (SFI) funded for 8 years by the Research Council of Norway and a consortium of private and public partners (grant no. 309439). We are at the international forefront in deep learning research for image analysis in particular and for multimodal learning in general.

My main position is as Professor in the UiT Machine Learning Group.

I am also an Adjunct Professor at Pioneer Centre for AI, University of Copenhagen & Norwegian Computing Center.

For a brief CV, please see "Attachments".

Contribute to our joint Future through Research

My motivation is to contribute solutions toward the pressing societal challenges of our time in health, within marine monitoring, for better exploitation of energy resources, and for precise observation of the Earth. I have extensive collaboration with industry and public sector stakeholders. My methodological research has focused on topics such as neural networks, information theoretic learning, kernel methods, unsupervised learning, self-supervised learning, and explainable AI (XAI). My research is regularly published in the most central conferences and journals in the field (ICLR, ICML, NeurIPS, etc). I have been fortunate to work with many good colleagues and together our research has been recognized by our peers in the field: 

Research (and teaching) Honors

• Best Paper Award, Pattern Recognition Letters (2024)
• Dissertation Award, Norwegian Artificial Intelligence Society (Trosten, co-supervisor, 2023)
• Best Paper Award, Colour and Visual Computing Symposium (2022)
• Best Paper Award Int’l Medical Informatics Association (2018)
• Outstanding Lecturer Award, Faculty of Science and Technology, UiT (2018)
• Best Student Paper Award, Scandinavian Conference on Image Analysis (supervisor) (2017)
• Winner of the IEEE GRS Society Letters Prize Paper Award (2013)
• Featured Paper, IEEE Transactions on Pattern Analysis and Machine Intelligence (2010)
• Received the University of Tromsø Young Investigator Award (a bi-annual award) (2007)
• Received the ICASSP Outstanding Student Paper Award (2005)
• Pattern Recognition Journal Best Paper Award, Honourable Mention (2003)

International Leadership (current)

• Scientific Advisory Board  (SAB) for the Max Planck Institute for Intelligent Systems https://is.mpg.de
• Scientific Advisory Board for one of the new French "AI Excellence Clusters" SequoIA, funded by France 2030 and administered by the French National Agency for Research (ANR)
• SAB for DIREC - Digital Research Centre Denmark https://direc.dk

Selected recent publications:

Google Scholar

Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders. ICML 2025. https://openreview.net/forum?id=jYmGi1175R

The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making. IEEE TPAMI 2025.

REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability. AAAI 2025. https://arxiv.org/abs/2412.08513

Guest Editor: Special Issue on Information Theoretic Methods for the Generalization, Robustness, and Interpretability of Machine Learning. IEEE TNNLS 2025. https://doi.org/10.1109/TNNLS.2025.3525991

Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks. ICML 2024. https://proceedings.mlr.press/v235/moller24a.html

MAP IT to visualize representations. ICLR 2024. https://openreview.net/pdf?id=OKf6JtXtoy

Cauchy-Schwarz divergence information bottleneck for regression. ICLR, 2024. https://openreview.net/pdf?id=7wY67ZDQTE

ADNet++: A few-shot learning framework for multi-class medical image volume segmentation with uncertainty-guided feature refinement. Medical Image Analysis, 2023. https://doi.org/10.1016/j.media.2023.102870

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings. CVPR, 2023. https://openaccess.thecvf.com/content/CVPR2023/html/Trosten_Hubs_and_Hyperspheres_Reducing_Hubness_and_Improving_Transductive_Few-Shot_Learning_CVPR_2023_paper.html

On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering. CVPR, 2023. https://openaccess.thecvf.com/content/CVPR2023/html/Trosten_On_the_Effects_of_Self-Supervision_and_Contrastive_Alignment_in_Deep_CVPR_2023_paper.html

RELAX: Representation Learning Explainability. International Journal of Computer Vision, 2023. https://doi.org/10.1007/s11263-023-01773-2

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model. NeurIPS, 2022. https://openreview.net/forum?id=L8pZq2eRWvX

Principle of Relevant Information for Graph Sparsification. UAI, 2022. https://proceedings.mlr.press/v180/yu22c.html

Anomaly Detection-inspired Few-shot Medical Image Segmentation through Self-supervision with Supervoxels. Medical Image Analysis, 2022. https://doi.org/10.1016/j.media.2022.102385

Clinically Relevant Features for Predicting the Severity of Surgical Site Infections. IEEE Journal of Biomedical and Health Informatics, 2021. https://doi.org/10.1109/JBHI.2021.3121038

Joint Optimization of an Autoencoder for Clustering and Embedding. Machine Learning, 2021. https://doi.org/10.1007/s10994-021-06015-5

Measuring Dependence with Matrix-based Entropy Functional. AAAI, 2021. https://doi.org/10.1609/aaai.v35i12.17288

Reconsidering Representation Alignment for Multi-view Clustering. CVPR, 2021. https://openaccess.thecvf.com/content/CVPR2021/papers/Trosten_Reconsidering_Representation_Alignment_for_Multi-View_Clustering_CVPR_2021_paper.pdf

Uncertainty-aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series. IEEE Journal of Biomedical and Health Informatics, 2020. https://doi.org/10.1109/JBHI.2020.3042637

SEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks. ECCV, 2020. https://link.springer.com/chapter/10.1007/978-3-030-58592-1_8