Tobias Uelwer

I am a data scientist at Fraunhofer IAIS and I am also affiliated with the Lamarr Institute for Machine Learning and Artificial Intelligence. Previously, I was a researcher in the Artificial Intelligence Group at the Technical University of Dortmund, where I completed my PhD under the supervision of Prof. Dr. Stefan Harmeling.

I obtained my Bachelor's and Master's degrees in computer science with a minor in mathematics from the Heinrich Heine University Düsseldorf.

Email / Google Scholar / DBLP / LinkedIn / Github

profile photo
Research Interests

My research is focused on deep neural networks and particularly their applications in image/signal processing, medicine, reinforcement learning, and natural language processing. I have worked on deep learning for solving inverse problems, such as phase retrieval and computed tomography. Furthermore, I am interested in adversarial attacks on deep learning models.


Selected Publications
A Survey on Self-Supervised Representation Learning
Tobias Uelwer, Jan Robine, Stefan Sylvius Wagner, Marc Höftmann, Eric Upschulte, Sebastian Konietzny, Maike Behrendt, Stefan Harmeling
ArXiv preprint (submitted to a journal)
paper / bibtex

This survey paper provides a comprehensive review of these methods in a unified notation, points out similarities and differences of these methods, and proposes a taxonomy which sets these methods in relation to each other.

Learning Conditional Generative Models for Phase Retrieval
Tobias Uelwer, Sebastian Konietzny, Alexander Oberstraß, Stefan Harmeling
Journal of Machine Learning Research (JMLR)
paper / bibtex

Conditional generative adversarial networks can be used to achieve state-of-the-art reconstructions for compressive and Fourier phase retrieval.

A previous version of this work was also presented at the International Conference on Pattern Recognition (ICPR) 2020.

Transformer-based World Models Are Happy With 100k Interactions
Jan Robine, Marc Höftmann, Tobias Uelwer, Stefan Harmeling
International Conference on Learning Representations (ICLR), 2023
paper / bibtex / code

We propose a transformer-based world model (TWM) that enhances sample efficiency and allows learning of long-term dependencies while staying computationally efficient..

This work was also presented at the NeurIPS 2022 Deep Reinforcement Learning Workshop.

Optimizing Intermediate Representations of Generative Models for Phase Retrieval
Tobias Uelwer*, Sebastian Konietzny*, Stefan Harmeling (*equal contribution)
Transactions on Machine Learning Research (TMLR)
paper / bibtex

Refined intermediate layer optimization of generative models and new learned initialization schemes perform exceptionally well at the Fourier and Gaussian phase retrieval problem.

This work was also presented at the NeurIPS 2022 AI4Science Workshop.

Evaluating Robust Perceptual Losses for Image Reconstruction
Tobias Uelwer, Felix Michels, Oliver De Candido
NeurIPS 2022 ICBINB Workshop - Understanding Deep Learning Through Empirical Falsification
paper / bibtex

We show that robust perceptual losses do not perform better than non-robust ones for image super-resolution.

Spirometry‐based reconstruction of real‐time cardiac MRI: Motion control and quantification of heart-lung interactions
Lena Maria Röwer, Tobias Uelwer, Janina Hußmann, Halima Malik, Monika Eichinger, Dirk Voit, Mark Oliver Wielpütz, Jens Frahm, Stefan Harmeling, Dirk Klee, Frank Pillekamp
Magnetic Resonance in Medicine, 2021
paper / bibtex / supplementary material

Real-time MRI combined with MR-compatible spirometry and retrospective binning can be used for image stabilization and offers opportunities to analyze heart-lung interactions.

PyMatting: A Python Library for Alpha Matting
Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling
Journal of Open Source Software (JOSS), 2020
paper / bibtex / repository / docs

PyMatting toolbox for Python which implements various approaches to solve the alpha matting problem. Our library is also able to extract the foreground of an image given the alpha matte.

On the Vulnerability of Capsule Networks to Adversarial Attacks
Felix Michels*, Tobias Uelwer*, Eric Upschulte*, Stefan Harmeling (*equal contribution)
ICML 2019 Workshop on Security and Privacy of Machine Learning
paper / bibtex / poster

This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks. Our experiments show that capsule networks can be fooled as easily as convolutional neural networks.

Service for the Scientific Community
  • Conferences/Workshops: TinyPapers@ICLR 2024 (Area Chair), AI4Science Workshop@ICML 2024, NeurIPS 2023, AABI Symposium@ICML 2023, ICANN 2023, ICML 2023, NeurIPS 2022 ICBINB Workshop, NeurIPS 2022 AI4Science Workshop, ICML 2022, ML Reproducibility Challenge 2021 Fall Edition, ICLR 2022, NeurIPS 2021 ICBINB Workshop, NeurIPS 2021, ICANN 2021, ICLR 2021, ML Reproducibility Challenge 2020, NeurIPS 2019 Reproducibility Challenge, NeurIPS 2019
  • Journals: Inverse Problems & Imaging, Optics Express, IEEE Transactions on Neural Networks and Learning Systems, Journal of Open Source Software
Teaching (as TA)

At Department of Computer Science at the Technical University of Dortmund:

  • Undergraduate Project: Reproducibility in Machine Learning Research: summer 2023
  • Probabilistic Reasoning and Machine Learning: winter 2022
  • Data Structures, Algorithms and Programming II: summer 2022

At the Department of Computer Science at the Heinrich Heine University:

  • Programming: winter 2020
  • Reinforcement Learning: summer 2020
  • Deep Learning: summer 2019, summer 2020, summer 2021
  • Machine Learning: winter 2017, winter 2018, winter 2019, winter 2020, winter 2021
  • Causality: summer 2018, summer 2019, summer 2021
  • Algorithms and Data Structures: winter 2015, winter 2018
  • Database Systems: winter 2015, winter 2017
  • C Programming: summer 2016
  • Theoretical Foundations of Computer Science: summer 2016
News
  • May 2024: I am starting a new position as data scientist at the Fraunhofer IAIS, where I will work on NLP.
  • August 2023: I successfully defended my PhD thesis and am now a doctor!
  • July 2023: I am co-organizer of this year's ICBINB workshop at NeurIPS 2023.
  • May 2023: I have received an outstanding Reviewer Award from the ML Reproducibility Challenge 2022.
  • November 2022: Tom, Jan, Sebastian, Stefan and I have won the Helsinki Tomography Challenge 2022.
  • April 2022: Our group is joining the Department of Computer Science at the Technical University of Dortmund.
  • May 2022: I have received an outstanding Reviewer Award from the ML Reproducibility Challenge 2021.
  • April 2020: I am volunteering for ICLR 2020.
  • March 2020: I am spending two weeks at the Max Planck Institute for Intelligent Systems in Tübingen.
  • August 2019: I am participating at the Machine Learning Summer School at the Skolkovo Institute of Science and Technology in Moscow.

This website is based on the template of Jon Barron's website. Used with permission.