Search Results - "Bitterwolf, Julian"

Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem by Hein, Matthias, Andriushchenko, Maksym, Bitterwolf, Julian

“…Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they…”
Get full text

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation by Bitterwolf, Julian, Müller, Maximilian, Hein, Matthias

“…Out-of-distribution (OOD) detection is the problem of identifying inputs which are unrelated to the in-distribution task. The OOD detection performance when…”
Get full text

Provably Robust Detection of Out-of-distribution Data (almost) for free by Meinke, Alexander, Bitterwolf, Julian, Hein, Matthias

“…The application of machine learning in safety-critical systems requires a reliable assessment of uncertainty. However, deep neural networks are known to…”
Get full text

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities by Bitterwolf, Julian, Meinke, Alexander, Augustin, Maximilian, Hein, Matthias

“…It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution…”
Get full text

Certifiably Adversarially Robust Detection of Out-of-Distribution Data by Bitterwolf, Julian, Meinke, Alexander, Hein, Matthias

“…Advances in Neural Information Processing Systems 33 (NeurIPS 2020) Deep neural networks are known to be overconfident when applied to out-of-distribution…”
Get full text

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem by Hein, Matthias, Andriushchenko, Maksym, Bitterwolf, Julian

“…Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they…”
Get full text

A simple way to make neural networks robust against diverse image corruptions by Rusak, Evgenia, Schott, Lukas, Zimmermann, Roland S, Bitterwolf, Julian, Bringmann, Oliver, Bethge, Matthias, Brendel, Wieland

“…The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the…”
Get full text