Artur Radzivil
Image:
Private

Artur Radzivil

My Research Stay at Visual Intelligence: Artur Radzivil

Artur Radzivil is a PhD Research Fellow at Vilnius Gediminas Technical University. He visited Visual Intelligence in Oslo from September to November 2025.

My Research Stay at Visual Intelligence: Artur Radzivil

Artur Radzivil is a PhD Research Fellow at Vilnius Gediminas Technical University. He visited Visual Intelligence in Oslo from September to November 2025.

By Petter Bjørklund, Communications Officer at SFI Visual Intelligence

My name is Artur Radzivil, and I am a PhD student at Vilnius Tech. My research focuses on deep learning for computer vision, specifically looking for ways to make object detection more robust and semantically aware.

The main goal of my research stay was to implement the Semantic Superpixel-based Tokenization (SPiT) method, developed by Marius Aasan at UiO, into the YOLO (You Only Look Once) architecture. Standard YOLO models operate on a rigid pixel grid, which can struggle with fragmented detections when objects blend into the background. By integrating superpixels—groups of pixels with similar semantic meaning—we aim to provide the model with better regional information.

During my stay, I conducted several experiments on small datasets (YOLOv12 Small Data) and began developing a dedicated YOLO-Superpixel framework. This work is currently a "work in progress," and we plan to continue this collaboration to bridge the gap between grid-based CNNs and graph-based semantic reasoning. I also had the opportunity to present this work as a poster during the VI Days 2025, titled "Integrating Semantic Superpixel-based Tokenization into the YOLO Architecture."

The outcome of this stay has been immensely valuable. Beyond the technical implementation, the collaborative environment at the University of Oslo (UiO) significantly sharpened my research methods. I am deeply grateful to the whole team for their support, insights, and help with my project.

Life in Norway was a unique and memorable experience. I lived in Åsgårdstrand at my father-in-law's place and commuted to Oslo by train almost every day. My workday often began on my laptop right there on the train, watching the beautiful Norwegian landscape pass by. What struck me most was the people—everyone I met was incredibly kind, pleasant, and welcoming. This blend of high-level academic work and the warm, friendly atmosphere of Norway made my stay truly special.

Latest news

Call for Papers and Abstracts: NLDL 2027

April 22, 2026

The Call for Papers and Abstracts for the Northern Lights Deep Learning (NLDL) Conference 2027 is officially announced – with submission deadlines on August 7th and Mid-September 2026 respectively.

Trends in Visual Intelligence 2026

April 17, 2026

The field of Visual Intelligence is continuously transforming. Chief Research Scientist Arnt-Børre Salberg dives deeper into the current trends in the field of visual intelligence as of early 2026.

Centre-developed seismic foundation model is now open source!

April 6, 2026

The NCS model, a seismic foundation model trained on data from the Norwegian data repository for subsurface data, is now available as an open-source model, allowing anyone to download, utilize, and further develop the model.

Visual Intelligence Annual Report 2025

March 31, 2026

The Visual Intelligence Annual Report 2025, highlighting the centre's progress, activities, achieved innovations, staff, funding, and publications for 2025, is now available to read on our websites.

Visual Intelligence strengthens ties with Pioneer Centre for AI in EHR-related research

March 26, 2026

Visual Intelligence researchers contributed to the Pioneer Centre for AI workshop on Electronic Health Records research. The aim was to strengthen ties between the two centres on EHR-related research.

Nordlys: Her blir KI-studentene grillet av sin «egen» teknologi

March 24, 2026

Tre av studentene i sivilingeniør i Kunstig Intelligens ved UiT skal delta i NM i KI. Slik gikk det da de ble intervjuet ved hjelp av kunstig intelligens (News article in nordlys.no).

My Research Stay at Visual Intelligence: Rami Al-Belmpeisi

March 15, 2026

Rami Al-Belmpeisi is a PhD Research Fellow in the Visual Computing section at DTU Compute, Technical University of Denmark. He visited Visual Intelligence in Tromsø from November 2025 to February 2026.

Visual Intelligence inspires future students at the UiT Open Day

March 12, 2026

Visual Intelligence researchers came to the UiT Open Day to inform the students about UiT's study programme, and inspire them to pursue AI-related studies and career paths.

Dagsavisen: Hun lærer kunstig intelligens å forstå medisinske bilder

March 4, 2026

Elisabeth Wetzer forsker på hvordan maskiner kan lære å analysere medisinske bilder – og samtidig forstå hva legene faktisk ser etter (Norwegian news article on dagsavisen.no)