no code implementations • 22 May 2023 • Jia Yu Tee, Oliver De Candido, Wolfgang Utschick, Philipp Geiger
Towards safe autonomous driving (AD), we consider the problem of learning models that accurately capture the diversity and tail quantiles of human driver behavior probability distributions, in interaction with an AD vehicle.
no code implementations • 9 Jul 2021 • Tobias Uelwer, Felix Michels, Oliver De Candido
Our method is able to detect adversarial examples generated by various attacks, and can be easily adopted to a plethora of deep classification models.
no code implementations • 27 May 2021 • Philipp Joppich, Sebastian Dorn, Oliver De Candido, Wolfgang Utschick, Jakob Knollmüller
This constitutes a statistical inference task in terms of the optimal latent space activations of the underlying uncorrupted datum.