Certified Robust Models with Slack Control and Large Lipschitz Constants

1 code implementation • 12 Sep 2023 • Max Losch, David Stutz, Bernt Schiele, Mario Fritz

In this paper, we propose a Calibrated Lipschitz-Margin Loss (CLL) that addresses this issue and improves certified robustness by tackling two problems: Firstly, commonly used margin losses do not adjust the penalties to the shrinking output distribution; caused by minimizing the Lipschitz constant $K$.

Interpretability Beyond Classification Output: Semantic Bottleneck Networks

no code implementations • 25 Jul 2019 • Max Losch, Mario Fritz, Bernt Schiele

Additionally we show how the activations of the SB-Layer can be used for both the interpretation of failure cases of the network as well as for confidence prediction of the resulting output.

Classification Dimensionality Reduction +2