Changkyu Choi introducing his Thesis.
Image:
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)

Supervisors

  • 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

Acknowledgement

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

Register for NLDL 2025!

October 4, 2024

Registration for the Northern Lights Deep Learning Conference 2025 is now open. The general deadline for registration is January 1st 2025.

Visual Intelligence at Forskningsdagene 2024

September 30, 2024

Visual Intelligence researchers participated in various dissemination activities throughout Forskningsdagene 2024. The activities aimed to disseminate general knowledge about deep learning and Visual Intelligence's research activities to the general public.

Another successful Visual Intelligence Days!

September 26, 2024

93 people from across the Visual Intelligence (VI) consortium gathered at Quality Airport Hotel Gardermoen for Visual Intelligence Days 2024, 24th to 25th of September.

Successful PhD defense by Ghadi Al Hajj

September 19, 2024

Congratulations to Ghadi Al Hajj for successfully defending his PhD thesis and achieving the degree of Philosophiae Doctor at the University of Oslo on September 16th 2024!

Nordlys: Klar med KI-utstilling

September 18, 2024

Kommende søndag er det åpen dag på Nordnorsk vitensenter. Der lanseres vitensenteret siste nyvinning, en interaktiv utstilling basert på kunstig intelligens (KI).

uit.no: Vil vekke barns interesse for kunstig intelligens med ny utstilling

September 12, 2024

Maskinlæringsgruppen på UiT og SFI Visual Intelligence har arbeidet med å lage en utstilling som skal øke barns interesse, nysgjerrighet, og forståelse for kunstig intelligens. Nå vil den være utstillingsklar under et åpent familiearrangement på Nordnorsk vitensenter 22 september

forskning.no: Slik kan kunstig intelligens finne mikroskopiske fossiler

September 10, 2024

Forskere har trent opp kunstig intelligens til å finne og kategorisere mikrofossiler. De tror arbeidet kan bli til stor nytte for geologer verden over (Norwegian news story at forskning.no).

Visual Intelligence represented at exclusive Nobel conference

August 29, 2024

Associate professor and PI Elisabeth Wetzer participated in this year's Lindau Nobel Laureate Meeting in Vienna, Austria. The conference is one of the world's largest annual gatherings for Nobel Prize winners.

NRK Radio: Artificial intelligence in the Norwegian health sector

August 15, 2024

Centre director Robert Jenssen was featured in an NRK Radio interview about the Arendalsuka event "Hvordan implementerer vi KI for bruk i helsesektoren på en trygg måte?"

Visual Intelligence represented at Arendalsuka 2024

August 14, 2024

Visual Intelligence was represented by director Robert Jenssen during the UiT event "Hvordan implementerer vi KI for bruk i helsesektoren på en trygg måte?". The event addressed how to safely implement artificial intelligence tools in the fields of health and medicine.

My Research Stay at Visual Intelligence: Jeff Clark

August 12, 2024

Jeff Clark is a Research Fellow in AI at University of Bristol and co-founder and CEO of IngeniumAI: a startup company in radiology AI from the University of Bath and Royal United Hospitals Bath NHS Trust. He visited Visual Intelligence in Tromsø from June to July 2024.

Research paper with Visual Intelligence researchers accepted for ECCV Workshop

August 2, 2024

Visual Intelligence congratulates Hyeongji Kim for getting her research paper "ProxyDR: Deep Hyperspherical Metric Learning with Distance Ratio-Based Formulation" accepted for a coming European Conference on Computer Vision (ECCV) Workshop"

My Research Stay at Visual Intelligence: María Castro Fernández

July 24, 2024

María Castro Fernández is a PhD Candidate at the Research Institute of Applied Microelectronics at Universidad de Las Palmas de Gran Canaria, in Spain. She visited Visual Intelligence in Tromsø from January to June 2024.