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

Towards a Foundation Model for Seismic Interpretation

By authors:

Ordonez, A; Wade, D; Ravaut, C; Waldeland A.U.

Published in:

85th EAGE Annual Conference & Exhibition, Jun 2024, Volume 2024, p.1 - 5

on

June 1, 2024

MAP IT to Visualize Representations

By authors:

Jenssen, Robert

Published in:

International Conference on Learning Representations 2024

on

May 7, 2024

Leveraging tensor kernels to reduce objective function mismatch in deep clustering

By authors:

Trosten, Daniel Johansen; Løkse, Sigurd Eivindson; Jenssen, Robert; Kampffmeyer, Michael Christian

Published in:

Pattern Recognition

on

May 1, 2024

Prototypical Self-Explainable Models Without Re-training

By authors:

Gautam, Srishti; Boubekki, Ahcene; Höhne, Marina Marie-Claire; Kampffmeyer, Michael Christian.

Published in:

Transactions on Machine Learning Research (TMLR)

on

May 1, 2024

DIB-X: Formulating Explainability Principles for a Self-Explainable Model Through Information Theoretic Learning

By authors:

C. Choi, S. Yu, M. Kampffmeyer, A. -B. Salberg, N. O. Handegard and R. Jenssen

Published in:

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 7170-7174

on

April 14, 2024

Deep-learning-derived input function in dynamic [18F]FDG PET imaging of mice

By authors:

Kuttner, Samuel; Luppino, Luigi Tommaso; Convert, Laurence; Sarrhini, Otman; Lecomte, Roger; Kampffmeyer, Michael Christian; Sundset, Rune; Jenssen, Robert.

Published in:

Frontiers in Nuclear Medicine

on

April 11, 2024

PTUS: Photo-Realistic Talking Upper-Body Synthesis via 3D-Aware Motion Decomposition Warping

By authors:

Lin, Luoyang; Jiang, Zutao; Liang, Xiaodan; Ma, Liqian; Kampffmeyer, Michael Christian; Cao, Xiaochun.

Published in:

Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3441-3449

on

March 24, 2024

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

By authors:

Chakraborty, Rwiddhi; Sletten, Adrian; Kampffmeyer, Michael Christian.

Published in:

Computer Vision and Pattern Recognition 2024

on

March 20, 2024

Defending Against Poisoning Attacks in Federated Learning with Blockchain

By authors:

Dong, Nanqing; Wang, Zhipeng; Sun, Jiahao; Kampffmeyer, Michael Christian; Knottenbelt, William; Xing, Eric.

Published in:

IEEE Transactions on Artificial Intelligence (TAI)

on

March 18, 2024

Interrogating Sea Ice Predictability With Gradients

By authors:

Joakimsen, H. L., Martinsen I., Luppino, L. T., McDonald, A., Hosking, S., and Jenssen, R.

Published in:

IEEE Geoscience and Remote Sensing Letters

on

February 14, 2024

Other publications

annual reports