85 citations · 182 across the 17 of their papers we have counts for
17 papers
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
Fanfei Li, Thomas Klein, Wieland Brendel +2
Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from robustness benchmarks to quantif…
In Search of Forgotten Domain Generalization
Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer +4
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets…
InfoNCE: Identifying the Gap Between Theory and Practice
Evgenia Rusak, Patrik Reizinger, Attila Juhos +3
Prior theory work on Contrastive Learning via the InfoNCE loss showed that, under certain assumptions, the learned representations recover the ground-truth latent factors. We argue…
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
Roland S. Zimmermann, Thomas Klein, Wieland Brendel
In light of the recent widespread adoption of AI systems, understanding the internal information processing of neural networks has become increasingly critical. Most recently, mach…
Don't trust your eyes: on the (un)reliability of feature visualizations
Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau +2
How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization…
Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Roland S. Zimmermann, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi +2
Self-supervised methods for learning object-centric representations have recently been applied successfully to various datasets. This progress is largely fueled by slot-based metho…
Provably Learning Object-Centric Representations
Jack Brady, Roland S. Zimmermann, Yash Sharma +3
Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While…
Increasing Confidence in Adversarial Robustness Evaluations
Roland S. Zimmermann, Wieland Brendel, Florian Tramer +1
Hundreds of defenses have been proposed to make deep neural networks robust against minimal (adversarial) input perturbations. However, only a handful of these defenses held up the…
Score-Based Generative Classifiers
Roland S. Zimmermann, Lukas Schott, Yang Song +2
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversa…
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Roland S. Zimmermann, Judy Borowski, Robert Geirhos +3
A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used ap…
Contrastive Learning Inverts the Data Generating Process
Roland S. Zimmermann, Yash Sharma, Steffen Schneider +2
Contrastive learning has recently seen tremendous success in self-supervised learning. So far, however, it is largely unclear why the learned representations generalize so effectiv…
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink +6
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional ne…
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Judy Borowski, Roland S. Zimmermann, Judith Schepers +4
Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural ne…
A simple way to make neural networks robust against diverse image corruptions
Evgenia Rusak, Lukas Schott, Roland S. Zimmermann +4
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image…
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"
Roland S. Zimmermann
A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adv…
Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control Tasks
Borja Fernandez-Gauna, Manuel Graña, Roland S. Zimmermann
We present Simion Zoo, a Reinforcement Learning (RL) workbench that provides a complete set of tools to design, run, and analyze the results,both statistically and visually, of RL…
Faster Training of Mask R-CNN by Focusing on Instance Boundaries
Roland S. Zimmermann, Julien N. Siems
We present an auxiliary task to Mask R-CNN, an instance segmentation network, which leads to faster training of the mask head. Our addition to Mask R-CNN is a new prediction head,…