Für eine korrekte Darstellung dieser Seite benötigen Sie einen XHTML-standardkonformen Browser, der die Darstellung von CSS-Dateien zulässt.


You are here

Professorin Dr.-Ing. Margret Keuper

H/C 8309

Universität Siegen
Lehrstuhl für Visual Computing
57076 Siegen

I joined the University of Siegen in August 2021 as a Professor for Visual Computing.
My research interests are Computer Vision and Machine Learning. More specifically, I am interested in problems such as

  • Learning Graph Embeddings and Graph Representations
  • Neural Architecture Search
  • Grouping Problems (in applications such as Image and Motion Segmentation and Multiple Object Tracking)
  • Efficient Solvers for Large Grouping Problems
  • Motion Estimation
  • Image Generation and Deep Fake Detection

Before, I worked as a Juniorprofessor for Computer Vision at the University of Mannheim and as a visiting researcher at MPII, Saarbrücken. During my PhD with Thomas Brox at the University of Freiburg, I focused on the segmentation in volumetric bio-medical image data. I am a member of the ELLIS society.

Recent Selected Publications

  • A. Saseendran, K. Skubsch, S. Falkner, M. Keuper, Trading-off Image Quality for Robustness is not necessary with Regularized Deterministic Autoencoders, accepted at NeurIPS 2022.
  • J. Grabinski, P. Gavrikov, J. Keuper, M. Keuper, Robust Models are Less Over-Confident, accepted at NeurIPS 2022. 
  • J. Lukasik, S. Jung, M. Keuper, Learning Where to Look -- Generative NAS is Surprisingly Efficient, accepted to ECCV 2022.
  • J. Grabinski, S. Jung, J. Keuper, M. Keuper, FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting, accepted to ECCV 2022.
  • S. Jung, M. Keuper, Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks, accepted to ECML-PKDD 2022.
  • E. Levinkov*, A. Kardoost*, B. Andres and M. Keuper (*equal contribution), "Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2022.3148795.
  • J. Siems, L. Zimmer, A. Zela, J. Lukasik, M. Keuper and F. Hutter, NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search, ICLR, 2022.
  • A. Saseendran, K. Skubch, S. Falkner, M. Keuper, Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders: , NeurIPS 2021.
  • S. Jung, M. Keuper, Spectral Distribution aware Image Generation, AAAI 2021.
  • Y. He, N. Yu, M. Keuper, M. Fritz, Beyond the Spectrum: Detecting Deepfakes by Image Re-Synthesis, IJCAI 2021.
  • A. Kardoost,  M. Keuper, Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation, UAI 2021.
  • A. Saseendran, K. Skubch, M. Keuper, Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation, ICCV 2021.