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

Pruning by explaining: A novel criterion for deep neural network prunin

By authors:

Yeom, Seul-Ki; Seegerer, Philipp; Lapuschkin, Sebastian; Binder, Alexander; Wiedemann, Simon; Müller, Klaus-Robert; Samek, Wojciech.

Published in:

Pattern Recognition

on

March 3, 2021

Measuring Dependence with Matrix‐Based Entropy Functional

By authors:

Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose Principe

Published in:

AAAI 2021

on

January 25, 2021

Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps

By authors:

Kristoffer Wickstrøm, Michael Kampffmeyer, Robert Jenssen

Published in:

Medical Image Analysis, Volume 60, February 2020, 101619

on

November 14, 2019

Pathloss prediction using deep learning with applications to cellular optimization and efficient D2D link scheduling

By authors:

Ron Levie, Çağkan Yapar, Gitta Kutyniok, Giuseppe Caire

Published in:

ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

on

May 4, 0202

Other publications

annual reports