Computer Vision and Machine Learning

At the University of Mannheim:

• Steffen Jung
• Shashank Agnihotri
• Tejaswini Medi
• Katharina Prasse
• Mishal Fatima

Alumni:

• Yumeng Li (Bosch BCAI)
• Patrick Müller
• Amrutha Saseendran (Bosch BCAI)
• Jovita Lukasik
• Amirhossein Kardoost
• Kalun Ho (Fraunhofer ITWM)

External PhD Students:

• Yushi Liu (Bosch BCAI)
• Yuxuan Zhou (CISPA)
• Julia Grabinski (Fraunhofer ITWM)

At the University of Mannheim, we are teaching the following courses:

Higher Level Computer Vision (CS 646)

Image Processing (CS 647)

Generative Computer Vision

Reinforcement Learning (IE 695)

Seminar: Computer Vision

News:

Y. Li, W. Beluch, M. Keuper, D. Zhang, A. Khoreva: VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis, accepted at ICLR 2025.

P. Gavrikov, J. Lukasik, S. Jung, R. Geirhos, M.J. Mirza, M. Keuper, J. Keuper: Can we talk models into seeing the world differently?, accepted at ICLR 2025.

J. Lukasik, M. Moeller, M. Keuper: An evaluation of zero-cost proxies-from neural architecture performance prediction to model robustness, International Journal of Computer Vision, 1–18, 2025.

K. Prasse, I. Bravo, S. Walter, M. Keuper: I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames,  accepted at WACV 2025.

T. Medi, S. Jung, M. Keuper: Fair-TAT: Improving Model Fairness Using Targeted Adversarial Training, arXiv preprint arXiv:2410.23142, accepted at WACV 2025.

S. Agnihotri, J. Grabinski, M. Keuper: Improving Feature Stability during Upsamping -- Spectral Artifacts and the Importance of Spatial Context, ECCV 2024.

P. Gavrikov, S. Agnihotri, M. Keuper, J. Keuper:  How Do Training Methods Influence the Utilization of Vision Models?, NeurIPS workshop: Interpretable AI: Past, Present and Future, 2024

K. Bäuerle, P. Müller, S. M. Kazim, I. Ihrke, M. Keuper: Learning the essential in less than 2k additional weights – a simple approach to improve image classification stability under corruptions, [openreview] [pdf] [bib], Transactions on Machine Learning Research (TMLR), 2024.

J. Grabinski, J. Keuper, M. Keuper: As large as it gets – Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters, [openreview] [pdf] [bib] [code], Transactions on Machine Learning Research (TMLR), 2024.

S. Agnihotri, S. Jung, M. Keuper: CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks (https://openreview.net/forum?id=CXZqGJonmt), ICML 2024.

Y. Zhou, M. Fritz, M. Keuper: MultiMax: Sparse and Multi-Modal Attention Learning (https://openreview.net/forum?id=IC9UZ8lm25), ICML 2024.

J. P. Schneider, M. Fatima, J. Lukasik, A. Kolb, M. Keuper, M. Moeller: Implicit Representations for Constrained Image Segmentation (https://openreview.net/forum?id=IaV6AgrTUp),  ICML 2024.

U. A. Kaplan, Y. Li, M. Keuper, A. Khoreva, and D. Zhang,  “Domain-Aware Fine-Tuning of Foundation Models,” in ICML 2024 Workshop on Foundation Models in the Wild (ICML 2024 FM-Wild Workshop), Vienna, Austria, 2024.

Y. Li, M. Keuper, D. Zhang, A. Khoreva: Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive (https://arxiv.org/abs/2401.08815),  ICLR 2024.

J. Lukasik, P. Gavrikov, J. Keuper, M. Keuper: Improving Native CNN Robustness with Filter Frequency Regularization, TMLR 2023.

Y. Li, M. Keuper, D. Zhang, A. Khoreva, Divide & Bind Your Attention for Improved Generative Semantic Nursing, BMVC 2023 (oral).

T. Medi, J. Tayyub, M. Sarmad, F. Lindseth, M. Keuper, FullFormer: Generating Shapes inside Shapes, GCPR 2023. 

K. Prasse, S. Jung, Y. Zhou, M. Keuper, Local Spherical Harmonics Improve Skeleton-based Hand Action Recognition, GCPR 2023.

J. Lukasik, J. Geiping, M. Möller, M. Keuper, Differentiable Architecture Search: a One-Shot Method?, AutoML Conference workshop, 2023.

P. Müller, A. Braun, M. Keuper,  Classification robustness to common optical aberrations, ICCV2023 AROW Workshop.

S. Agnihotri, K.V. Gandikota, J. Grabinski, P. Chandramouli, M. Keuper, On the unreasonable vulnerability of transformers for image restoration and an easy fix, ICCV2023 AROW Workshop

An Evaluation of Zero-Cost Proxies -- from Neural Architecture Search to Model Robustness, J. Lukasik, M. Möller, M. Keuper, accepted at GCPR, 2023. 

An extended Benchmark Study of Human-Like Behavior under Adversarial Training,  P. Gavrikov, J. Keuper, M. Keuper, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023.

Improving Primary-Vertex Reconstruction with a Minimum Cost lifted Multicut Graph Partitioning Algorithm, V. Kostyukhin, M. Keuper, I. Ibragimov, N. Owtscharenko, M. Cristinziani, Journal of Instrumentation (JINST) , 2023.

Neural Architecture Design and Robustness: A Dataset, S. Jung, J. Lukasik, M. Keuper,  ICLR 2023.

Intra-Source Style Augmentation for Improved Domain Generalization, Y. Li, D. Zhang, M. Keuper, A. Khoreva, WACV 2023.

Trading-off Image Quality for Robustness is not necessary with Regularized Deterministic Autoencoders, A. Saseendran, K. Skubsch, S. Falkner, M. Keuper, NeurIPS 2022.              

Robust Models are Less Over-Confident, J. Grabinski, P. Gavrikov, J. Keuper, M. Keuper, NeurIPS 2022. 

Learning Where to Look -- Generative NAS is Surprisingly Efficient, J. Lukasik, S. Jung, M. Keuper, ECCV 2022.

FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting, J. Grabinski, S. Jung, J. Keuper, M. Keuper, ECCV 2022.

Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks, S. Jung, M. Keuper, ECML-PKDD 2022.

Higher-Order Multicuts for Geometric Model Fitting and Motion Segmentation, E. Levinkov*, A. Kardoost*, B. Andres and M. Keuper (*equal contribution),  in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2022.3148795.

NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search, J. Siems, L. Zimmer, A. Zela, J. Lukasik, M. Keuper and F. Hutter,  ICLR, 2022.

Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders , A. Saseendran, K. Skubch, S. Falkner, M. Keuper,  NeurIPS 2021.

Spectral Distribution aware Image Generation, S. Jung, M. Keuper, AAAI 2021.

Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space, K. Ho, F.-J. Pfreundt, J Keuper, M Keuper,  https://arxiv.org/abs/2106.12303

Beyond the Spectrum: Detecting Deepfakes by Image Re-Synthesis, Y He, N Yu, M Keuper, M Fritz, accepted at IJCAI 2021

Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation, A Kardoost, M Keuper,  arXiv preprint arXiv:2105.07469, accepted at UAI 2021

Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation, A Saseendran, K Skubch, M Keuper, arXiv preprint arXiv:2103.16795

SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain, P Harder, FJ Pfreundt, M Keuper, J Keuper, arXiv preprint arXiv:2103.03000, accepted at IJCNN 2021

Learning embeddings for image clustering: An empirical study of triplet loss approaches, K Ho, J Keuper, FJ Pfreundt, M Keuper, 2020 25th International Conference on Pattern Recognition (ICPR), 87–94

Object Segmentation Tracking from Generic Video Cues, A Kardoost, S Müller, J Weickert, M Keuper, 2020 25th International Conference on Pattern Recognition (ICPR), 623–630

Smooth variational graph embeddings for efficient neural architecture search, J Lukasik, D Friede, A Zela, F Hutter, M Keuper, arXiv preprint arXiv:2010.04683, accepted at IJCNN 2021

You can also find a full list of my publications on Google Scholar.