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

Addressing Distribution Shifts in Federated Learning for Enhanced Generalization Performance

June 1, 2023
By
Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick, Grigorios Chrysos, Volkan Cevher

On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering

March 6, 2023
By
Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer.

All publications

Federated Learning under Covariate Shifts with Generalization Guarantees

By authors:

Ali Ramezani-Kebrya, Fanghui Liu, Thomas Pethick, Grigorios Chrysos, Volkan Cevher

Published in:

Transactions on Machine Learning Research

on

June 1, 2023

Distributed extra-gradient with optimal complexity and communication guarantees

By authors:

Ali Ramezani-Kebrya, Kimon Antonakopoulos, Igor Krawczuk, Justin Deschenaux, Volkan Cevher

Published in:

International Conference on Learning Representations ICLR 2023

on

May 1, 2023

Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI

By authors:

Cepeda, Santiago and Luppino, Luigi Tommaso and Pérez-Núñez, Angel and Solheim, Ole and García-García, Sergio and Velasco-Casares, María and Karlberg, Anna and Eikenes, Live and Sarabia, Rosario and Arrese, Ignacio and Zamora, Tomás and Gonzalez, Pedro and Jiménez-Roldán, Luis and Kuttner, Samuel

Published in:

Cancers. 2023; 15(6):1894.

on

March 22, 2023

On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering

By authors:

Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer.

Published in:

CVPR 2023

on

March 6, 2023

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings

By authors:

Daniel J. Trosten*, Rwiddhi Chakraborty*, Sigurd Løkse, Kristoffer Knutsen Wickstrøm, Robert Jenssen, Michael Kampffmeyer (* indicates equal contribution)

Published in:

CVPR 2023

on

March 6, 2023

The Kernelized Taylor Diagram

By authors:

Kristoffer Wickstrøm, Juan Emmanuel Johnson, Sigurd Eivindson Løkse, Gusatu Camps-Valls, Karl Øyvind Mikalsen, Michael Kampffmeyer, and Robert Jenssen

Published in:

NAIS 2022 Communications in Computer and Information Science, vol 1650. Springer

on

February 2, 2023

Deep Semisupervised Semantic Segmentation in Multifrequency Echosounder Data

By authors:

Changkyu Choi, Michael Kampffmeyer, Nils Olav Handegard, Arnt-Børre Salberg and Robert Jenssen

Published in:

IEEE Journal of Oceanic Engineering

on

February 1, 2023

A Generalized Geodesic Distance-Based Approach for Analysis of SAR Observations Across Polarimetric Modes

By authors:

Debanshu Ratha, Andrea Marinoni and Torbjørn Eltoft

Published in:

IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-16, 2023

on

December 23, 2022

A self-guided anomaly detection-inspired few-shot segmentation network

By authors:

Suaiba Amina Salahuddin, Stine Hansen, Srishti Gautam, Michael Kampffmeyer, Robert Jenssen

Published in:

CEUR Workshop Proceedings 2022, Volum 3271.

on

November 13, 2022

Gated information bottleneck for generalization in sequential environments

By authors:

Francesco Alesiani, Shujian Yu and Xi Yu

Published in:

Knowledge and Information Systems (KAIS)

on

October 31, 2022

Other publications

annual reports