Menu

News

Announcements, paper acceptances, talks, and lab highlights.

2025

  1. DFG Funds Research on Reliable AI for Open-World Object Detection

    DFG Funds Research on Reliable AI for Open-World Object Detection

    Project DFG UOS

    The German Research Foundation (DFG) has approved funding for a new research project led by Matthias Rottmann at Osnabrück University.

  2. ICCV2025 Paper Acceptance

    ICCV2025 Paper Acceptance

    ICCV2025 Paper

    Our work "TARS Traffic-Aware Radar Scene Flow Estimation" by Jialong Wu , Marco Braun, Dominic Spata and Matthias Rottmann (Aptiv, Bergische Universität Wuppertal) has been accepted for publication at ICCV2025.

  3. Team Event in Bochum

    Team Event in Bochum

    Team event

    Our team headed underground at the German Mining Museum to see massive, century-old machinery in action and learn about 200 years of Ruhr region mining history—all while escaping the summer heat above.

  4. Workshop with CARIAD

    Workshop with CARIAD

    Workshop

    On June 12th, the ACM AI-Lab at the University of Wuppertal hosted a collaborative workshop with CARIAD, the software and technology company within the Volkswagen Group.

  5. Research Visit from Australia

    We were delighted to host Dr. Maryam Haghighat from the Department of Electrical Engineering and Robotics at the Queensland University of Technology in Brisbane, Queensland, Australia, for a two-week research visit in June.

  6. Just Scan It 3D Project Meeting at the German Mining Museum

    Just Scan It 3D Project Meeting at the German Mining Museum

    Project Team event

    On April 11, 2025, the Just Scan It 3D project held its second meeting at the German Mining Museum (Deutsches Bergbaumuseum) in Bochum, hosted by Professor Michael Prange and the museum itself. Our team, along with all other project participants, gathered for a productive day.

  7. Girls’ Day 2025 with the ACM AI Lab

    Girls’ Day 2025 with the ACM AI Lab

    On April 3, as part of Girls' Day, two groups of schoolgirls visited us.

  8. New paper on Shape Bias & Robustness Evaluation released

    New paper on Shape Bias & Robustness Evaluation released

    Paper

    Our work on Shape Bias & Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation was published.

  9. Workshop with Control Expert

    Workshop with Control Expert

    Workshop

    On February 7, 2025, a joint workshop with Control Expert took place at Campus Freudenberg. The event provided a platform for exchange between industry partners and our research team.

2024

  1. BMVC Workshop

    BMVC Workshop

    Workshop

    On November 27, 2024, we hosted the Workshop on Robust Recognition in the Open World (RROW) in collaboration with Hermann Blum, Hanno Gottschalk, Kira Maag and Siniša Šegvić.

  2. OOD Detection: Limits of Open-Vocabulary Object Detectors

    OOD Detection: Limits of Open-Vocabulary Object Detectors

    Paper ECCV2024

    Up to now, there has only been a limited number of scientific works on how to teach object detection systems to detect unknown objects, so-called out-of-distribution (OOD) objects, e.g. objects that typically do not appear in street scenes.

  3. Workshop at dSPACE

    Workshop at dSPACE

    Workshop

    Today we had a wonderful workshop at dSPACE with the team of Nikolas Hemion.

  4. Workshop on Robust Recognition in the Open World at BMVC2024

    Workshop on Robust Recognition in the Open World at BMVC2024

    Workshop BMVC2024

    The ACM AI Lab is co-organizing a BMVC2024 workshop (https://rrow2024.github.io/) end of November in Glasgow Scotland.

  5. Paper accepted for publication in the proceedings of BMVC2024

    Paper accepted for publication in the proceedings of BMVC2024

    Paper BMVC2024

    Our work with colleagues from EPFL's CVLab has been accepted for publication at BMVC.

  6. New paper has been accepted for presentation at ECAI2024 in Santiago de Compostela

    New paper has been accepted for presentation at ECAI2024 in Santiago de Compostela

    Paper ECAI2024

    Our paper, titled "Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion", has been accepted for presentation at ECAI2024 in Santiago de Compostela!

  7. Paper accepted for publication in the proceedings of ECCV2024

    Paper accepted for publication in the proceedings of ECCV2024

    Paper ECCV2024

    Our paper "SparseRadNet Sparse Perception Neural Network on Subsampled Radar Data" has been accepted for publication in the proceedings of ECCV2024!

  8. Participation at the DataNinja sAIOnARA 2024 Conference

    Participation at the DataNinja sAIOnARA 2024 Conference

    Sarina Penquitt and Matthias Rottmann (associated DataNinjas) participated at the DataNinja sAIOnARA 2024 conference from June 25th to June 27th, 2024 at Bielefeld University.

  9. ACM AI Lab at University of Wuppertal's summer fest

    ACM AI Lab at University of Wuppertal's summer fest

    BUW

    The ACM AI Lab, part of the Interdisciplinary Center for Machine Learning and Data Analytics (IZMD), took part in the University of Wuppertal's summer fest.

  10. Exchange with the Centre for Robotics at Queensland University of Technology in Australia

    Exchange with the Centre for Robotics at Queensland University of Technology in Australia

    Supported by the German Academic Exchange Service (DAAD), Annika Mütze and Matthias Rottmann visited Dimity Miller and Niko Sünderhauf at the Centre for Robotics, Queensland University of Technology in Brisbane, Australia.

  11. Scientific Workshop at ControlExpert GmbH

    Scientific Workshop at ControlExpert GmbH

    Workshop

    We had the pleasure to be guests of ControlExpert GmbH who hosted a scientific exchange with deep dives into the cutting-edge topics aoround dep learning.

  12. Uncertainty estimation for semantic segmentation and its application to insurance industry

    Uncertainty estimation for semantic segmentation and its application to insurance industry

    Our industry partner ControlExpert (CE), part of Allianz SE, demonstrates how methods for uncertainty quantification in semantic segmentation can be of use in automated motor claim handling in the insurance industry.

2023

  1. Two Preprints Accepted for Presentation at VISIGRAPP 2024 in Rome, Italy

    Two Preprints Accepted for Presentation at VISIGRAPP 2024 in Rome, Italy

    Paper VISIGRAPP2024

    Both papers contribute to the advancement of data-centric artificial intelligence.

  2. Digital workshop with Continental

    Digital workshop with Continental

    Workshop

    Today Continental — our partner in KI Familie projects — and us had another very pleasant digital joint workshop with many fruitful discussions on trustworthy and efficient AI.

  3. DAAD supports cooperation with Queensland University of Technology, QUT Center for Robotics

    DAAD supports cooperation with Queensland University of Technology, QUT Center for Robotics

    Project DAAD QUT BUW

    The collaboration between Niko Suenderhauf, Dimity Miller from Queensland University of Technology, our colleague Annika Mütze and Matthias Rottmann has been selected for fundin...

  4. Inaugural Lecture by Matthias Rottmann

    Inaugural Lecture by Matthias Rottmann

    On October 24, 2023, PD Dr. Matthias Rottmann gave his inaugural lecture at the Department of Mathematics and Computer Science, Faculty of Mathematics and Natural Sciences, at the University of Wuppertal.

  5. Paper accepted for publication in the proceedings of WACV2024

    Paper accepted for publication in the proceedings of WACV2024

    Paper WACV2024

    Our paper "Identifying Label Errors in Object Detection Datasets by Loss Inspection" has been accepted for publication in the proceedings of WACV2024!

  6. Making automated driving safer: RELiABEL project launched

    Making automated driving safer: RELiABEL project launched

    Project BMFTR UOS

    As part of the RELiABEL project, scientists at the University of Wuppertal are researching how to make the interpretation of image data for automated driving more reliable in th...

  7. Paper accepted for publication at ICCV workshops

    Paper accepted for publication at ICCV workshops

    Paper ICCV2023

    Sarina Penquitt and Matthias Rottmann (associated DataNinjas) participated at the DataNinja sAIOnARA 2024 conference from June 25th to June 27th, 2024 at Bielefeld University.

  8. DataNinja association of S. Penquitt and M. Rottmann

    DataNinja association of S. Penquitt and M. Rottmann

    Since September 2023, Sarina Penquitt and Matthias Rottmann are officially associated members of the DataNinjas.

  9. Paper acceptance at GCPR 2023

    Paper acceptance at GCPR 2023

    Paper GCPR2023

    Our paper „LMD Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds“ has been accepted for publication and oral presentation at GCPR 2023.

  10. Workshop with visitors from Queensland University of Technology

    Workshop with visitors from Queensland University of Technology

    Workshop

    Today we had a very inspiring workshop with our guests Dimity Miller and Niko Sünderhauf from Queensland University of Technology, Center for Robotics at the University of Wuppertal, IZMD.

  11. Girlsday 2023 School of Mathematics and Natural Sciences

    Girlsday 2023 School of Mathematics and Natural Sciences

    Today we supported the girlsday 2023 at the University of Wuppertal with a number of curious and enthusiastic girls.

  12. Our team joins the Applied and Computational Mathematics group

    Our team joins the Applied and Computational Mathematics group

    BUW

    As of today, our junior research group on reliable and efficient AI is part of the Applied and Computational Mathematics (ACM) group in the Department of Mathematics and Computer Science.

2022

  1. BMBF Junior Research Group UnrEAL

    BMBF Junior Research Group UnrEAL

    Project BMFTR BUW

    Making the use of artificial intelligence safer: Funding for scientists from Wuppertal Artificial intelligence (AI) is used in many areas of our daily lives: when shopping onlin...

  2. Paper accepted for publication in the proceedings of NeurIPS2022

    Paper accepted for publication in the proceedings of NeurIPS2022

    Our joint work with Technical University of Dortmund entitled „UQGAN A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs“ has been accepted for publication in the proceedings of NeurIPS 2022.