Follow
Roland Simon Zimmermann
Title
Cited by
Cited by
Year
A simple way to make neural networks robust against diverse image corruptions
E Rusak, L Schott, RS Zimmermann, J Bitterwolf, O Bringmann, M Bethge, ...
ECCV 2020 (Oral), 2020
235*2020
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX
J Rauber, R Zimmermann, M Bethge, W Brendel
Journal of Open Source Software 5 (53), 2607, 2020
1882020
Contrastive Learning Inverts the Data Generating Process
RS Zimmermann, Y Sharma, S Schneider, M Bethge, W Brendel
ICML 2021 (Spotlight) 139, 12979-12990, 2021
1842021
Observing spatio-temporal dynamics of excitable media using reservoir computing
RS Zimmermann, U Parlitz
Chaos: An Interdisciplinary Journal of Nonlinear Science 28 (4), 2018
1512018
Faster training of Mask R-CNN by focusing on instance boundaries
RS Zimmermann, JN Siems
Computer Vision and Image Understanding, 102795, 2019
742019
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
J Borowski, RS Zimmermann, J Schepers, R Geirhos, TSA Wallis, ...
ICLR 2021, 2020
41*2020
Score-based generative classifiers
RS Zimmermann, L Schott, Y Song, BA Dunn, DA Klindt
NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, 2021
362021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
RS Zimmermann, J Borowski, R Geirhos, M Bethge, T Wallis, W Brendel
NeurIPS 2021 (Spotlight), 2021
232021
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"
RS Zimmermann
arXiv preprint arXiv:1907.00895, 2019
182019
Provably Learning Object-Centric Representations
J Brady, RS Zimmermann, Y Sharma, B Schölkopf, J von Kügelgen, ...
ICML 2023 (Oral), 2023
132023
Don't trust your eyes: on the (un) reliability of feature visualizations
R Geirhos, RS Zimmermann, B Bilodeau, W Brendel, B Kim
arXiv preprint arXiv:2306.04719, 2023
92023
Increasing Confidence in Adversarial Robustness Evaluations
RS Zimmermann, W Brendel, F Tramer, N Carlini
NeurIPS 2022, 2022
92022
Reconstructing Complex Cardiac Excitation Waves From Incomplete Data Using Echo State Networks and Convolutional Autoencoders
S Herzog, RS Zimmermann, J Abele, S Luther, U Parlitz
Frontiers in Applied Mathematics and Statistics 6, 616584, 2021
72021
A self-supervised feature map augmentation (FMA) loss and combined augmentations finetuning to efficiently improve the robustness of CNNs
N Kapoor, C Yuan, J Löhdefink, R Zimmerman, S Varghese, F Hüger, ...
Proceedings of the 4th ACM Computer Science in Cars Symposium, 1-8, 2020
52020
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
RS Zimmermann, T Klein, W Brendel
NeurIPS 2023 (Spotlight), 2023
32023
Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
RS Zimmermann, S van Steenkiste, MSM Sajjadi, T Kipf, K Greff
arXiv preprint arXiv:2305.18890, 2023
32023
Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control Tasks
B Fernandez-Gauna, M Graña, RS Zimmermann
arXiv preprint arXiv:1904.07817, 2019
12019
Measuring Mechanistic Interpretability at Scale Without Humans
RS Zimmermann, DA Klindt, W Brendel
ICLR 2024 Workshop on Representational Alignment, 2024
2024
Content suppresses style: dimensionality collapse in contrastive learning
E Rusak, P Reizinger, RS Zimmermann, O Bringmann, W Brendel
NeurIPS 2022 Workshop: Self-Supervised Learning - Theory and Practice, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–19