Changkyu Choi introducing his Thesis.
Harald Lykke Joakimsen

Changkyu Choi introducing his Thesis.

High Quality PhD defense in the Visual Intelligence research centre

Changkyu Choi defended his PhD thesis “Advancing Deep Learning for Marine Environment Monitoring” on June 9th 2023 at UiT The Arctic University of Norway.

High Quality PhD defense in the Visual Intelligence research centre

The key objectives of Changkyu Choi thesis is advancing both deep learning and marine environment monitoring, this by addressing the challenges linked to limited annotated data. Choi has develop a new explainable deep learning method that generates explanations tailored to the needs and preferences of the  users and evaluated these in the  context of marine environment monitoring.

Changkyu Choi (center) with comitee and advisors. (Photo Harald Lykke Joakimsen)

Evaluation Committee

  • Associate Prof. Vedrana Dahl, Department of Applied Mathematics and Computer Science, Technical University of Denmark (1. Opponent)
  • Prof. Morten Goodwin, Department of Information and communication technology, University of Agder (2. Opponent)
  • Associate Prof. Benjamin Ricaud, Department of Physics and Technology, UiT (internal member and leader of the committee)


  • Professor Robert Jenssen, Department of Physics and Technology, UiT (main supervisor)
  • Associate Prof. Michael C. Kampffmeyer, Department of Physics and Technology, UiT (co-supervisor)
  • Senior Researcher Arnt-Børre Salberg, Norwegian Computing Centre (co-supervisor)

Summary of thesis

Marine environment monitoring has become increasingly significant due to the excessive exploitation of oceans, which detrimentally impacts ecosystems. Deep learning provides an effective monitoring approach by automating the analysis of vast amounts of observed image data, enabling stakeholders to make informed decisions regarding fishing quotas or conservation efforts. The success of deep learning is often attributed to its capacity to extract relevant features from data, without the need for handcrafted rules or heuristics. However, this capability is not without limitations, as the intricate feature extraction process of deep learning-based systems poses fundamental challenges. A lack of annotated data presents an inherent challenge for deep learning. The widespread success of deep learning has primarily relied on the ample availability of annotated data, while deep learning models encounter difficulties when learning from limited annotations. However, obtaining annotated data is expensive, particularly in the context of marine environment monitoring, as it is often a manual process demanding the expertise of domain specialists. Another challenge of deep learning is a lack of explainability. The black-box nature of deep learning models can make it difficult to understand how they arrive at their decisions. This hinders their adoption in critical decision-making processes, as stakeholders may be hesitant to trust models whose decision-making rationale is not transparent or interpretable. To address the challenges and further advance deep learning methodologies, this thesis proposes three novel deep learning methods, highlighting marine environment monitoring as an application domain.

Link to thesis in Munin


The PhD project was a collaboration between Institute of Marine Research, The Norwegian computing center and UiT The Arctic University of Norway. The project was funded by COGMAR and Visual Intelligence.

Latest news

Klare for å levere toppforskning og innovasjon innen kunstig intelligens (KI)

September 7, 2023

Visual intelligence og norske forskningssentre innen kunstig intelligens er klare til å bidra til regjeringens ambisiøse milliardsatsning på KI for å utvikle trygg, pålitelig, og effektiv kunstig intelligens som vil gagne samfunnet, innovasjonen og utdanningen.

Well received PhD defense at the Visual Intelligence Research Centre

August 23, 2023

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.

Vil du formidle forsking på og kunnskap om kunstig intelligens?

August 23, 2023

Ledig stilling som kommunikasjonsrådgiver i forskningsruppe for maskinlæring. Vi søker engasjert formidler som kan øke vår synlighet ved å formidle vår forskning til et bredt publikum.

Tromsø AI Meetup 2023: A gathering to inspire and connect AI enthusiasts

June 12, 2023

The Tromsø AI Meetup 2023 brought together AI enthusiasts at Storgata Camping to connect, learn from notable speakers, and explore the exciting developments in AI, fostering a community passionate about responsible innovation in the field.

Undervannsrobot – fra konstruksjon til forskning

May 11, 2023

Fjernstyrte undervannsroboter er et viktig verktøy i kartlegging, utforskning og overvåkning av verdens havområder. I slutten av april fikk 22 elever fra videregående skoler i Troms og Finnmark designe, bygge og anvende fjernstyrte undervannsroboter.

Pitchday 2023

May 5, 2023

A pitch day was organized at UiT for to connect students with companies for external master’s projects and job opportunities in computer science and machine learning.

Visit by Prof. Pierre Baldi, University of California, Irvine

March 15, 2023

Prof. Pierre Baldi visited Visual Intelligence in Tromsø, February 16-17, 2023. The two days were filled with fruitful meetings on potential scientific collaboration between UCI and Visual Intelligence.

Visual Intelligence PhD students at UiT open day

March 6, 2023

Machine learning phd students from Visual Intelligence present at UiT The Arctic University of Norway's open day 2023, for recruitment of new students.

VIGS trip to Skibotn!

March 3, 2023

VIGS is Visual Intelligence's social and scientific initiative for phd students, postdocs and early career researchers! May 3-5 VIGS will organize a joint trip to UiT's field station in Indre Troms. Sign up and read more about the social and scientific program in out event!

Excellent PhD defense in the Visual Intelligence research centre

December 19, 2022

Stine Hansen defended her PhD thesis “Leveraging Supervoxels for Medical Image Volume Segmentation With Limited Supervision” on Dec. 16th at UiT The Arctic University of Norway.

Report from the VIGS gathering in Tromsø

December 1, 2022

7-8 November VIGS organized a successful gathering for early career researchers in Tromsø. The program was filled with both a social and technical program and gathered around 20 researchers from the research partners in Visual Intelligence.

Visual Intelligence visits by Lars Kai Hansen and Irina Voiculescu

November 16, 2022

We had the great pleasure of hosting Lars Kai Hansen, Technical University of Denmark, and Irina Voiculescu, University of Oxford, at the Visual Intelligence centre in Tromsø.