Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Bjoern M. Eskofier, Dario Zanca

Abstract: The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world ...