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

Federated Partially Supervised Learning With Limited Decentralized Medical Images

By authors:

Dong, Nanqing; Kampffmeyer, Michael; Voiculescu, Irina; Xing, Eric

Published in:

IEEE Transactions on Medical Imaging 2023 ;Volum 42.(7) s.1944-1954

on

December 20, 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

Cartoon Explanations of Image Classifiers

By authors:

Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, and Gitta Kutyniok

Published in:

European Conference on Computer Vision, 443-458, Springer Nature Switzerland

on

October 23, 2022

To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy

By authors:

Vignesh Srinivasan, Nils Strodthoff, Jackie Ma, Alexander Binder, Klaus-Robert Müller, and Wojciech Samek

Published in:

PLOS ONE 2022 ;Volume 17.(10)

on

October 18, 2022

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

By authors:

Srishti Gautam, Ahcene Boubekki, Stine Hansen, Suaiba Salahuddin, Robert Jenssen, Marina Höhne, Michael Kampffmeyer

Published in:

NeurIPS 2022

on

September 15, 2022

ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

By authors:

Xujie Zhang, Yu Sha, Michael Kampffmeyer, Zhenyu Xie, Zequn Jie, Chengwen Huang, Jianqing Peng, Xiaodan Liang

Published in:

ACM Multimedia (ACM MM 2022)

on

August 11, 2022

Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks

By authors:

Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

Published in:

International Journal of Remote Sensing, 2022

on

July 1, 2022

Learning Underrepresented Classes from Decentralized Partially Labeled Medical Images

By authors:

Nanqing Dong, Michael Kampffmeyer, Irina Voiculescu

Published in:

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022)

on

June 30, 2022

Principle of Relevant Information for Graph Sparsification

By authors:

Shujian Yu, Francesco Alesiani, Wenzhe Yin, Robert Jenssen and Jose C. Principe

Published in:

Conference on Uncertainty in Artificial Intelligence (UAI) 2022

on

May 20, 2022

Other publications

annual reports