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.
We congratulate PhD Fellow Suaiba Salahuddin, who will start as new Head Engineer at the Climate-Ecological Observatory for Arctic Tundra (COAT)
.jpg)
Researchers at Visual Intelligence have developed AI to predict the risk of getting breast cancer within one to five years. It can help detect more cases of breast cancer earlier.
Visual Intelligence researchers contributed with various activities during Forskningsdagene 2026: Norway's annual research festival.
100 researchers, user partners and invited guests gathered in Oslo, Norway for the Visual Intelligence Days: the centre's annual conference for sharing knowledge and updates on the latest research and innovations.
Why should we think twice before using AI as a therapist, romantic partner, or to help out with homework? AI expert Elisabeth Wetzer explains (Popular science article on sciencenorway.no / forskning.no).
Associate Professor Kristoffer Wickstrøm was interviewed by Norsk rikskringkasting (NRK) about the ongoing debate on whether to halt current and future AI development
Representatives from the Research Council of Norway came to Visual Intelligence's hub in Tromsø for a site visit meeting.
.jpg)
Harald Lykke Joakimsen, a PhD Candidate at Visual Intelligence's hub in Tromsø, will compete in Forsker Grand Prix: Norway's national popular science competition.
.png)
Congratulations to Centre Director Robert Jenssen, who was appointed as a new fellow of the International Associaton for Pattern Recognition (IAPR).
.jpg)
Why should we think twice before using AI as a therapist, romantic partner, or to help with homework? AI expert Elisabeth Wetzer explains.
Athinoulla Konstantinou is a PhD student at the University of Aberdeen. She visited Visual Intelligence's hub in Tromsø to work with equivariant modelling.
Visual Intelligence gathered experts from Norwegian politics, research council, industry, the public sector, and academia to discuss the value of Norwegian AI competence and Norwegian-developed models.
Visual Intelligence researchers are attending two AI-oriented events at Arendalsuka 2026: Norway's largest annual political festival.
Visual Intelligence hosted over 45 international AI researchers for the DL2026 workshop at UiT The Arctic University of Norway.
Visual Intelligence will be well represented at MICCAI 2026, one of the leading AI conferences on medical imaging and computer assisted intervention, with two accepted research papers.
Visual Intelligence co-organized and attended the "Foundations of Arctic AI and Generative Forecasting": an inaugural workshop in the P1 Arctic AI program.
PhD Candidates Solveig Thrun and Christian Salomonsen attended the Datacloud Global Congress' Talent in Tech programme, which invited emerging talent to a unique programme designed to inspire, educate, and connect young professionals with senior leaders from global tech giants.
We warmly welcome Georgios Leontidis as a new Professor at SFI Visual Intelligence's hub at UiT The Arctic University of Norway.
Centre Director Robert Jenssen was interviewed by Norsk rikskringkasting (NRK) about the Japan-Norway AI Innovation Forum in Tokyo, Japan.
En ny AI-løsning utviklet ved UiT kan gjøre det enklere å avdekke feilrapportering og ulovlig fiske. Nå skal Norges Råfisklag teste teknologien i praktisk bruk (News article on kystogfjord.no)