News
You are here
Research:
Our research focus is Computer Vision, Visual Computing and Machine Learning, specifically
- Learning Graph Embeddings and Graph Representations
- Neural Architecture Search
- Grouping Problems (in vision 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
We also have prior work on the segmentation in volumetric bio-medical image data.
News:
Recently published papers:
- 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.
- P Lorenz, D Strassel, M Keuper, J Keuper, Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness? The AAAI-22 Workshop on Adversarial Machine Learning and Beyond, 2022.
- J Grabinski, J Keuper, M Keuper, Aliasing coincides with CNNs vulnerability towards adversarial attacks The AAAI-22 Workshop on Adversarial Machine Learning and Beyond, 2022.
- K. Ho, FJ Pfreundt, J Keuper, M Keuper, Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space, The AAAI-22 Workshop on Adversarial Machine Learning and Beyond, 2022.
- S Jung, M Keuper, Internalized Biases in Fréchet Inception Distance, NeurIPS 2021 Workshop on Distribution Shifts, 2021.
- J Geiping, J Lukasik, M Keuper, M Moeller, DARTS for Inverse Problems: a Study on Hyperparameter Sensitivity (link is external), NeurIPS workshop on Inverse Problems, 2021.
- K Ho, A Chatzimichailidis, M Keuper, J Keuper, MSM: Multi-stage Multicuts for Scalable Image Clustering(link is external, International Conference on High Performance Computing, 267-284, 2021.
- P Lorenz, P Harder, D Straßel, M Keuper, J Keuper, Detecting AutoAttack Perturbations in the Frequency Domain (link is external), ICML 2021 Workshop on Adversarial Machine Learning
- S Jung, M Keuper, Spectral Distribution aware Image Generation (link is external), AAAI 2021
- Y He, N Yu, M Keuper, M Fritz, Beyond the Spectrum: Detecting Deepfakes by Image Re-Synthesis (link is external), IJCAI 2021
- A Kardoost, M Keuper, Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation (link is external), UAI 2021
- A Saseendran, K Skubch, M Keuper, Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation (link is external), ICCV 2021
Bachelor and Master Theses:
We are new at the University of Siegen, so we still have capacities to supervise Bachelor and Master Theses. Note that prior knowledge in our fields of research (e.g. gained by attending the lectures on Digital Image Processing, Deep Learning, etc.) is a requirement to be able to write a final thesis with us. If you study computer science and would like to form a project group (Projektgruppe) in the field of machine learning and/or visual computing, please contact Margret Keuper at margret.keuper@uni-siegen.de.