Daniel Johansen Trosten defended his PhD thesis “Improving Representation Learning for Deep Clustering and Few-shot Learning” on August 23rd 2023 at UiT The Arctic University of Norway.
Daniel Johansen Trosten defended his PhD thesis “Improving Representation Learning for Deep Clustering and Few-shot Learning” on August 23rd 2023 at UiT The Arctic University of Norway.
Summary of thesis:
The amounts of data in the world have increased dramatically in recent years, and it is quickly becoming infeasible for humans to label all these data. It is therefore crucial that modern machine learning systems can operate with few or no labels.The introduction of deep learning and deep neural networks has led to impressive advancements in several areas of machine learning. These advancements are largely due to the unprecedented ability of deep neural networks to learn powerful representations from a wide range of complex input signals. This ability is especially important when labeled data is limited, as the absence of a strong supervisory signal forces models to rely more on intrinsic properties of the data and its representations.
This thesis focuses on two key concepts in deep learning with few or no labels. First, we aim to improve representation quality in deep clustering - both for single-view and multi-view data. Current models for deep clustering face challenges related to properly representing semantic similarities, which is crucial for the models to discover meaningful clusterings. This is especially challenging with multi-view data, since the information required for successful clustering might be scattered across many views. Second, we focus on few-shot learning, and how geometrical properties of representations influence few-shot classification performance. We find that a large number of recent methods for few-shot learning embed representations on the hypersphere. Hence, we seek to understand what makes the hypersphere a particularly suitable embedding space for few-shot learning.
Evaluation Committee:
- Professor Klaus-Robert Müller, Technical University of Berlin, Germany (1. Opponent)
- Professor Anne H Schistad Solberg, Institute for Informatics, University of Oslo, Norway (2. Opponent)
- Professor Fred Godtliebsen, Department of Mathematics and Statistics (internal member and leader of the committee)
Supervisors:
- Associate Professor Michael Kampffmeyer, Department of Physics and Technology, UiT (main supervisor)
- Professor Robert Jenssen Department of Physics and Technology, UiT (co-supervisor)
- Researcher Sigurd Løkse, Department of Physics and Technology, UiT(co-supervisor)
The Defense was led by Professor John Sigurd Mjøen Svendsen, Pro-Dean at the Faculty of Science and Technology at UiT.
Visual Intelligence researchers have developed an AI to automatically measure the heart's structure – both quickly and accurately. They believe it can help doctors detect and treat cardiovascular diseases faster.
Samuel Kuttner and Elin Kile presented research on PET and artificial intelligence at evening seminar on early detection of prostate cancer organized by the Norwegian Prostate Cancer Assocation.
Centre Director Robert Jenssen represented Visual Intelligence at Svarte Natta 2025 – North Norway's journalist and media conference organized by the Norwegian Union of Journalists.
Congratulations to PhD Candidate Preetraj Bhoodoo, who recently won the Best Poster Presentation Award at the PRESIMAL Autumn Reserach School 2025.
We happily welcome Sigurd Almli Hanssen and Adrian Duric as new PhD Candidates at SFI Visual Intelligence's hubs in Tromsø and Oslo respectively.
AI expert Eirik Agnalt Østmo explains that the law is intended to make AI technology safe for everyone (Popular science article on sciencenorway.no)
Aitor Sánchez is a PhD candidate at the Intelligent Systems Group of the University of the Basque Country in Spain. He visited Visual Intelligence in Tromsø from March to June 2025.
We happily welcome Nicolo Grometto as a new PhD Candidate at SFI Visual Intelligence in Bodø, Norway.
Visual Intelligence hosted a hybrid meeting with researchers from the Alan Turing Institute at UiT The Arctic University of Norway in Tromsø, Norway.
Visual Intelligence researchers participated in this year's Forskningsdagene: an annual national research festival which aims to stimulate the general public's interest and curiosity in research.
Norge arbeider med å få på plass en egen lov for kunstig intelligens. Loven skal passe på at vi bruker KI på en trygg måte (Norwegian news article at uit.no).
85 researchers from the Visual Intelligence consortium convened for the Visual Intelligence Days: the annual workshop where researchers, user partners and invited guests convene to share knowledge and updates on the latest research and innovations within the centre.
Registration for the Northern Lights Deep Learning Conference 2026 is officially open. Early bird fees are available before December 1st 2025.
Det skal eksperter på kunstig intelligens, cybersikkerhet og juss fra UiT Norges arktiske universitet diskutere på Verdensteatret Kino den 17. september. Arrangementet er gratis og åpen for alle (Norwegian news article at uit.no)
The presentations from the Visual Intelligence Workshop on Foundation Models are now available on the Visual Intelligence YouTube channel.
Congratulations to Nikita Shvetsov for successfully defending his PhD thesis and achieving the PhD degree in Science at UiT The Arctic University of Norway on August 27th 2025.
Det sa digitaliseringsminister Karianne Tung (Ap) da hun besøkte UiT Norges arktiske universitet i Tromsø for å lære mer om utdanning og toppforskning på kunstig intelligens ved universitetet (Norwegian news article at uit.no)
A new study shows how deep learning can achieve human-level performance in estimating uncertainty when classifying foraminifera (News story at EurekAlert.org)
Congratulations to Iver Martinsen and Durgesh Kumar Singh, who successfully defended their PhD theses at UiT The Arctic University of Norway on August 20th and 21st respectively.
Visual Intelligence brought together academia, industry, the institute sector, the Research Council of Norway, and Norwegian politics to discuss why and how Norwegian academia and industry should collaborate more closely to develop innovative artificial intelligence.