I am a PhD student at the University of Tübingen and the Max Planck Research School for Intelligent Systems (IMPRS-IS), working in the lab of Matthias Bethge under the supervision of Wieland Brendel. At the moment, I’m interning at Google Brain. Earlier, I’ve completed my Bachelors and Masters from the University of Göttingen, and spent some time doing research at Volkswagen and BMW.

I started doing research on object detection and segmentation. In the recent past I have primarily worked on understanding failure cases of machine learning models in computer vision tasks through the lense of adversarial perturbations and common corruptions. This lead me to my next goal: aligning the decision process of machines with that of humans by recreating the natural learning process and inducing priors.

Current research interests: self-supervised learning, adversarial robustness, disentanglement, XAI

Latest Publications

NeurIPS 2022

Increasing Confidence in Adversarial Robustness Evaluations

Zimmermann, R. S., Brendel, W., Tramer, F., and Carlini, N.

NeurIPS 2021

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?

Zimmermann*, R. S., Borowski*, J., Geirhos, R. , Bethge, M., Wallis, T. S. A. and Brendel, W.

workshop

Score-Based Generative Classifiers

Zimmermann, R. S., Schott, L., Song, Y. Dunn, B. A. and Klindt, D. A.

More publications