Scholar
Steffen Jung
Google Scholar ID: x5ovaJcAAAAJ
Max Planck Institute for Informatics
Citations & Impact
Citations
304
H-index
9
i10-index
9
Publications
19
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks, ICML 2024
- Happy People -- Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models, CVPR 2023 Workshop on Generative Models for Computer Vision
- Neural Architecture Design and Robustness: A Dataset, ICLR 2023
- Learning Where To Look -- Generative NAS is Surprisingly Efficient, ECCV 2022
- FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting, ECCV 2022
- Optimizing Edge Detection for Image Segmentation with Multicut Penalties, GCPR 2022
- Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks, ECML PKDD 2022
- Internalized Biases in Fréchet Inception Distance, NeurIPS 2021 Workshop on Distribution Shifts
- Spectral Distribution aware Image Generation, AAAI 2021
Education
- Ph.D. in Computer Vision, Max Planck Institute for Informatics, Saarbrücken (Supervisor: Prof. Dr. Margret Keuper), 11/2020 – Present
- Co-affiliation with University of Siegen, 10/2022 – 12/2023
- Co-affiliation with University of Mannheim, since 01/2024
- M.Sc. Data and Web Science, University of Mannheim, 08/2017 – 10/2020
- Exchange Semester at University of Adelaide, 02/2019 – 07/2019
Background
- Area of Interest: Image Generation, Robustness, Learning for Combinatorial Optimization in Computer Vision
Miscellany
- Contact: mail (at) jung.vision, +49 176 801 484 39; Links to personal websites: ORCID, Google Scholar, dblp, Semantic Scholar, GitHub, YouTube, LinkedIn
Co-authors