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

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

Modular Superpixel Tokenization in Vision Transformers

August 28, 2024
By
Marius Aasan, Odd Kolbjørnsen, Anne Schistad Solberg, Adín Ramirez Rivera

All publications

Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation

By authors:

Srishti Gautam, Marina M.-C. Höhne, Stine Hansen, Robert Jenssen and Michael Kampffmeyer

Published in:

IEEE International Symposium on Biomedical Imaging (ISBI) 2022

on

February 1, 2022

Explain and improve: LRP-inference fine-tuning for image captioning models

By authors:

Sun, Jiamei; Lapuschkin, Sebasian; Samek, Wojciech; Binder, Alexander.

Published in:

Information Fusion, Volume 77, 2022, Pages 233-246

on

January 1, 2022

Towards robust partially supervised multi-structure medical image segmentation on small-scale data

By authors:

Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Min Xu, Irina Voiculescu and Eric Xing

Published in:

Applied Soft Computing, Volume 114, 2022

on

January 1, 2022

Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN

By authors:

Zhenyu Xie, Zaiyu Huang, Fuwei Zhao, Haoye Dong, Michael Kampffmeyer, Xiaodan Liang

Published in:

Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

on

December 23, 2021

Machine Learning + Marine Science: Critical Role of Partnerships in Norway

By authors:

Nils Olav Handegard, Line Eikvil, Robert Jenssen, Michael Kampffmeyer, Arnt-Børre Salberg, and Ketil Malde

Published in:

Journal of Ocean Technology 2021

on

October 6, 2021

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

By authors:

Daniel J. Trosten, Robert Jenssen, and Michael C. Kampffmeyer

Published in:

Vol. 2 (2021): Proceedings of the Northern Lights Deep Learning Workshop 2021

on

September 11, 2021

Self-supervised Multi-task Representation Learning for Sequential Medical Images

By authors:

Dong, N., Kampffmeyer, M., Voiculescu, I.

Published in:

Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12977. Springer, Cham

on

September 11, 2021

Semi-supervised target classification in multi-frequency echosounder data

By authors:

Changkyu Choi, Michael Kampffmeyer, Nils Olav Handegard, Arnt-Børre Salberg, Olav Brautaset, Line Eikvil, Robert Jenssen

Published in:

ICES Journal of Marine Science, Volume 78, Issue 7, October 2021, Pages 2615–2627

on

August 12, 2021

Instance Segmentation of Microscopic Foraminifera

By authors:

Johansen, Thomas Haugland; Sørensen, Steffen Aagaard; Møllersen, Kajsa; Godtliebsen, Fred

Published in:

Applied Sciences 2021 ;Volum 11.(14)

on

July 16, 2021

Joint optimization of an autoencoder for clustering and embedding

By authors:

Ahcène Boubekki, Michael Kampffmeyer, Ulf Brefeld, Robert Jenssen

Published in:

Machine Learning (2021)

on

June 21, 2021

Other publications

annual reports