314 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Charité - Universitätsmedizin BerlinDE17 papers
- Technische Universität BerlinDE8 papers
- Humboldt-Universität zu BerlinDE6 papers
- Freie Universität BerlinDE5 papers
- University of CopenhagenDK4 papers
- Bernstein Center for Computational Neuroscience BerlinDE3 papers
- ETH ZurichCH3 papers
- King's College LondonGB3 papers
- Lawrence Berkeley National LaboratoryUS3 papers
- Arcada University of Applied SciencesFI2 papers
- Birmingham City UniversityGB2 papers
- Cornell UniversityUS2 papers
3 papers · 1 filter
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
Sidney Bender, Ole Delzer, Jan Herrmann +3
Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-super…
Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Florian Bley, Jacob Kauffmann, Simon León Krug +2
Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practic…
Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena
Philip Naumann, Jacob Kauffmann, Grégoire Montavon
Wasserstein distances provide a powerful framework for comparing data distributions. They can be used to analyze processes over time or to detect inhomogeneities within data. Howev…