Scientific publications

At Visual Intelligence we work across our innovation areas to extract knowledge from large volumes of visual data more efficiently through automatic and intelligent data analysis. The work to address the core research challenges in deep learning: working with limited training data, utilizing context and dependencies, providing explainability, confidence and uncertainty, are important in all the innovation areas.

Featured blog posts

AI matches human experts in classifying microscopic organisms

July 16, 2025
By
Iver Martinsen, Steffen Aagaard Sørensen, Samuel Ortega, Fred Godtliebsen, Miguel Tejedor, Eirik Myrvoll-Nilsen

Visual Data Diagnosis and Debiasing with Concept Graphs

September 26, 2024
By
Chakraborty, Rwiddhi; Wang, Yinong; Gao, Jialu; Zheng, Runkai; Zhang, Cheng; De la Torre, Fernando

All publications

A lightweight and extensible cell segmentation and classification model for H&E-stained cancer whole slide images

By authors:

Nikita Shvetsov, Thomas Karsten Kilvær, Masoud Tafavvoghi, Anders Sildnes, Kajsa Møllersen, Lill-Tove Rasmussen Busund, Lars Ailo Bongo

Published in:

Computers in Biology and Medicine, Volume 199, 2025

on

December 1, 2025

SPoT: Subpixel Placement of Tokens in Vision Transformers

By authors:

Martine Hjelkrem-Tan, Marius Aasan, Gabriel Y. Arteaga, and Adín Ramírez Rivera

Published in:

Workshop on Efficient Computing under Limited Resources: Visual Computing (ICCV 2025), Oct 19 – 23th, 2025, Honolulu, Hawai'i

on

October 19, 2025

FLEXtime: Filterbank Learning to Explain Time Series

By authors:

Thea Brüsch, Kristoffer Wickstrøm, Mikkel N. Schmidt, Robert Jenssen, Tommy Sonne Alstrøm

Published in:

Explainable Artificial Intelligence. xAI 2025. Communications in Computer and Information Science, vol 2579. Springer

on

October 14, 2025

From Colors to Classes: Emergence of Concepts in Vision Transformers

By authors:

Teresa Dorszewski, Lenka Tětková, Robert Jenssen, Lars Kai Hansen, Kristoffer Knutsen Wickstrøm

Published in:

Communications in Computer and Information Science, vol 2576. Springer 2025

on

October 12, 2025

WOODWORK: A deep-learning based framework for woodpecker damage detection in powerline inspection

By authors:

Duy Khoi Tran, Van Nhan Nguyen, Kristoffer Wickstrøm, Michael Kampffmeyer

Published in:

International Journal of Electrical Power & Energy Systems, Volume 171, 2025, 110900, ISSN 0142-0615

on

October 1, 2025

Low-Rank Adaptations for increased Generalization in Foundation Model features

By authors:

Vilde Schulerud Bøe, Andreas Kleppe, Sebastian Foersch, Daniel-Christoph Wagner, Lill-Tove Rasmussen Busund, Adín Ramírez Rivera

Published in:

MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL), DAEJEON, South Korea, 2025

on

September 27, 2025

VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction

By authors:

Zijun Sun, Solveig Thrun, Michael Kampffmeyer

Published in:

Medical Image Computing and Computer Assisted Intervention – MICCAI 2025. MICCAI 2025. Lecture Notes in Computer Science, vol 15974. Springer

on

September 18, 2025

WiseLVAM: A Novel Framework For Left Ventricle Automatic Measurements

By authors:

Durgesh Kumar Singh, Qing Cao, Sarina Thomas, Ahcène Boubekki, Robert Jenssen, Michael Kampffmeyer

Published in:

Simplifying Medical Ultrasound, ASMUS 2025 Workshop, MICCAI 2025

on

September 17, 2025

VMRA-MaR: An Asymmetry-Aware Temporal Framework for Longitudinal Breast Cancer Risk Prediction

By authors:

Zijun Sun, Solveig Thrun and Michael Kampffmeyer

Published in:

MICCAI 2025

on

September 17, 2025

Tied Prototype Model for Few-Shot Medical Image Segmentation

By authors:

Hyeongji Kim, Stine Hansen, Michael Kampffmeyer

Published in:

MICCAI 2025

on

September 17, 2025

Other publications

annual reports