CURRICULUM VITAE

Steffen Jung

...

Contact

icon mail
mail (at) jung.vision
icon mail
+49 176 801 484 39
ORCID
Google Scholar
dblp
Semantic Scholar
GitHub
YouTube
LinkedIn

Area of Interest

Image Generation, Robustness, Learning for Combinatorial Optimization in Computer Vision

Experience

11/2020 – Present
Ph.D. in Computer Vision
Max Planck Institute for Informatics, Saarbrücken

University of Siegen (co-affiliation 10/2022 – 12/2023)

University of Mannheim (co-affiliation since 01/2024)
Supervisor: Prof. Dr. Margret Keuper

01/2024 – 04/2024
Research Visit
University of Maryland, group of Tom Goldstein
08/2017 – 10/2020
M.Sc. Data and Web Science
University of Mannheim
02/2019 – 07/2019
Exchange Semester
University of Adelaide

Awards

02/2019
Baden-Württemberg-STIPENDIUM
08/2018
Deutschlandstipendium

Selected Publications

06/2024
CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks
ICML 2024, arXiv, code
06/2023
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, arXiv
05/2023
Neural Architecture Design and Robustness: A Dataset
ICLR 2023, project page
10/2022
Learning Where To Look -- Generative NAS is Surprisingly Efficient
ECCV 2022, arXiv, poster
10/2022
FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
ECCV 2022, arXiv, poster
09/2022
Optimizing Edge Detection for Image Segmentation with Multicut Penalties
GCPR 2022, arXiv, poster
09/2022
Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks
ECML PKDD 2022, arXiv, poster
12/2021
Internalized Biases in Fréchet Inception Distance
NeurIPS 2021 Workshop on Distribution Shifts, OpenReview, poster
02/2021
Spectral Distribution aware Image Generation
AAAI 2021, arXiv, poster, code


updated May 2024, Impressum