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.
.jpg)
Congratulations to associate professor Ali Ramezani-Kebrya for receiving a prestigious FRIPRO grant from the Research Council of Norway!
KI har en tendens til å behandle menn og kvinner ulikt. Ekspert mener teknologien reproduserer gamle fordommer (Norwegian news story in NRK.no)
To UiT-forskere ser store etiske og juridiske problemer ved bruk av kunstig intelligens i kommunal saksbehandling (Norwegian news story in Nordlys.no).
Michael Kampffmeyer is one of UiT's youngest professors and has already distinguished himself through his contributions to AI research. He has now won UiT's award for young researchers at the university's annual celebration.
The fifth Visual Intelligence annual report, showcasing the centre's activities, results, staff, funding and publications for 2024, is now available on our web pages.
.jpg)
I juni møtes det norske KI-miljøet i Tromsø for å presentere ny forskning og diskutere nye retninger innen feltet. KI-forskere inviteres til å delta og vise fram forskningen sin under konferansen.
Visual Intelligence and the Digital Innovation Lab invited industry professionals to present ideas for master's projects to computer science and machine learning students at UiT The Arctic University of Norway.
Kunstig intelligens (KI) endrer måten vi løser komplekse problemer på. Ved UiT Norges arktiske universitet leder professor Robert Jenssen Visual Intelligence, et senter for forskningsdrevet innovasjon som utvikler neste generasjons KI-metoder.
Visual Intelligence researchers had the great pleasure of talking to high school students about the AI study programme at UiT The Arctic University of Norway during the UiT Open Day.
Director Robert Jenssen represented Visual Intelligence at the CuttingEdgeAI seminar "KI anno 2023: I offentlighetens interesse?" at the University of Bergen on March 7th.
Det hender at kunstig intelligens behandler menn og kvinner ulikt. Hvordan skjer dette? KI-forsker Elisabeth Wetzer forklarer hva som ligger bak skjevhetene i teknologien (Popular science story in forskning.no and sciencenorway.no)
Congratulations to Visual Intelligence board member Viktoria Gulliksen Stray for being featured in Abelia and ODA-Nettverk's list of Top 50 Influential Tech Women in Norway 2025!
Norwegian Minister of Research and Higher Education, Sigrun Aasland (Ap) got to hear about Visual Intelligence's work toward developing the next generation of deep learning methodology at a visit to UiT in Tromsø
Hva er lov og hva er ikke lov? Det er blant spørsmålene studentene stiller seg. (NRK.no story featuring director Robert Jenssen)
We had the pleasure of talking to students about the exciting career opportunities at Visual Intelligence and UiT The Arctic University of Norway during TEKdagen 2025
Last week, we welcomed students from Breivang upper secondary school to a full-day practical session on AI and programming at UiT The Arctic University of Norway
We happily welcome Solveig Thrun, who recently started as a doctoral research fellow at Visual Intelligence in Tromsø in January 2025.
Visual Intelligence and UiT researchers organized a special curricular course on collaborative coding and reproducible research at UiT The Arctic University of Norway.
Andrew McDonald, a PhD student from University of Cambridge and the British Antarctic Survey, presented his work on sea ice forecasting with diffusion models, as well as the downstream applications of those forecasts, at Visual Intelligence in Tromsø.
Deep learning researchers from 27 different countries congregated at the 8th edition of the NLDL conference. - I have seen several interesting posters and talks that have opened my mind about different paths to explore in my own research, says NLDL 2025 attendee Tiago Ramos.