F
Felix A. Wichmann
Researcher at University of Tübingen
Publications - 168
Citations - 11669
Felix A. Wichmann is an academic researcher from University of Tübingen. The author has contributed to research in topics: Psychophysics & Computer science. The author has an hindex of 40, co-authored 160 publications receiving 9212 citations. Previous affiliations of Felix A. Wichmann include Technical University of Berlin & Katholieke Universiteit Leuven.
Papers
More filters
Journal ArticleDOI
The psychometric function: I. Fitting, sampling, and goodness of fit
Felix A. Wichmann,N. Jeremy Hill +1 more
TL;DR: An integrated approach to fitting psychometric functions, assessing the goodness of fit, and providing confidence intervals for the function’s parameters and other estimates derived from them, for the purposes of hypothesis testing is described.
Posted Content
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos,Patricia Rubisch,Claudio Michaelis,Matthias Bethge,Felix A. Wichmann,Wieland Brendel +5 more
TL;DR: It is shown that ImageNet-trained CNNs are strongly biased towards recognising textures rather than shapes, which is in stark contrast to human behavioural evidence and reveals fundamentally different classification strategies.
Journal ArticleDOI
Shortcut learning in deep neural networks
Robert Geirhos,Jörn-Henrik Jacobsen,Claudio Michaelis,Richard S. Zemel,Wieland Brendel,Matthias Bethge,Felix A. Wichmann +6 more
TL;DR: A set of recommendations for model interpretation and benchmarking is developed, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.
Proceedings Article
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos,Patricia Rubisch,Claudio Michaelis,Matthias Bethge,Felix A. Wichmann,Wieland Brendel +5 more
TL;DR: In this paper, the same standard architecture that learns a texture-based representation on ImageNet is able to learn a shapebased representation instead when trained on "Stylized-ImageNet", a stylized version of ImageNet.
Journal ArticleDOI
The psychometric function: II. Bootstrap-based confidence intervals and sampling.
Felix A. Wichmann,NJ Hill +1 more
TL;DR: The present paper’s principal topic is the estimation of the variability of fitted parameters and derived quantities, such as thresholds and slopes, and introduces improved confidence intervals that improve on the parametric and percentile-based bootstrap confidence intervals previously used.