10 papers
LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds
Tobias Riedlinger, Marius Schubert, Sarina Penquitt +7
Object detection on Lidar point cloud data is a promising technology for autonomous driving and robotics which has seen a significant rise in performance and accuracy during recent…
MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions
Antonia van Betteray, Matthias Rottmann, Karsten Kahl
Current state-of-the-art deep neural networks for image classification are made up of 10 - 100 million learnable weights and are therefore inherently prone to overfitting. The comp…
Matrix functions via linear systems built from continued fractions
Andreas Frommer, Karsten Kahl, Manuel Tsolakis
A widely used approach to compute the action of a matrix function on a vector is to use a rational approximation for and compute instead. If …
MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection
Marius Schubert, Karsten Kahl, Matthias Rottmann
In object detection with deep neural networks, the box-wise objectness score tends to be overconfident, sometimes even indicating high confidence in presence of inaccurate predicti…
Coarsening in Algebraic Multigrid using Gaussian Processes
Hanno Gottschalk, Karsten Kahl
Multigrid methods have proven to be an invaluable tool to efficiently solve large sparse linear systems arising in the discretization of partial differential equations (PDEs). Alge…
A multigrid accelerated eigensolver for the Hermitian Wilson-Dirac operator in lattice QCD
Andreas Frommer, Karsten Kahl, Francesco Knechtli +3
Eigenvalues of the Hermitian Wilson-Dirac operator are of special interest in several lattice QCD simulations, e.g., for noise reduction when evaluating all-to-all propagators. In…