no code implementations • 27 May 2024 • Maximilian Granz, Manuel Heurich, Tim Landgraf
Recent advances in out-of-distribution (OOD) detection on image data show that pre-trained neural network classifiers can separate in-distribution (ID) from OOD data well, leveraging the class-discriminative ability of the model itself.
1 code implementation • ICML 2020 • Leon Sixt, Maximilian Granz, Tim Landgraf
The paper provides a framework to assess the faithfulness of new and existing modified BP methods theoretically and empirically.