Sparse Activations for Interpretable Disease Grading

We propose an inherently interpretable model that combines the feature extraction capabilities of deep neural networks with advantages of sparse linear models in interpretability.

Hidden in Plain Sight: Subgroup Shifts Escape OOD Detection

We demonstrate the limitations of OOD detection for subgroup shifts, i.e. shifts within the support of the original distribution. We show how such shifts can be detected on a population level instead and establish a baseline on histopathology images.