42 citations · 42 across the 3 of their papers we have counts for
3 papers
cs.LG2026
RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction
Manuel Heurich, Maximilian Granz, Tim Landgraf
Recent advances in uncertainty quantification for time series forecasting show that conformal prediction can provide reliable prediction intervals, yet standard conformal methods a…
cs.LG2024
WeiPer: OOD Detection using Weight Perturbations of Class Projections
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, leveragi…
cs.LG2019★ 42 cited
When Explanations Lie: Why Many Modified BP Attributions Fail
Leon Sixt, Maximilian Granz, Tim Landgraf
Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score…