4 papers
Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors
Peter Lorenz, Mario Fernandez, Jens Müller +1
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in real-world scenarios. In recent years, many OOD detectors have been developed, a…
On the Convergence Rate of Gaussianization with Random Rotations
Felix Draxler, Lars Kühmichel, Armand Rousselot +3
Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, h…
Finding Competence Regions in Domain Generalization
Jens Müller, Stefan T. Radev, Robert Schmier +3
We investigate a "learning to reject" framework to address the problem of silent failures in Domain Generalization (DG), where the test distribution differs from the training distr…
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Jens Müller, Robert Schmier, Lynton Ardizzone +2
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness i…