Oliver Bringmann — accepted AI-conference papers

2025

InfoNCE: Identifying the Gap Between Theory and Practice

Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel

AISTATS 2025poster

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 that these theories overlook crucial aspects of how CL is deployed in practice. Specifically, they either assume equal…

Cited by 0 Source ↗Scholar ↗

2020

A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions

Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge +1

ECCV 2020poster

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 recognition models strongly degrades when evaluated on previously unseen corruptions. Here, we demonstrate that a simple…

Cited by 244 Source ↗PDF ↗code ↗Scholar ↗

2020

Improving robustness against common corruptions by covariate shift adaptation

Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge

NeurIPS 2020poster

Today’s state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model robustness against common corruptions (like ImageNet-C) undere…

Cited by 597 Source ↗PDF ↗code ↗Scholar ↗