4 papers
Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation
Naga Venkata Sai Jitin Jami, Thomas Altstidl, Sebastian Hoefler +4
Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test splits. Reported accuracy has b…
You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows
Jonas Leo Mueller, Sebastian Hoefler, Dario Zanca +3
Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Ye…
Stratify or Die: Rethinking Data Splits in Image Segmentation
Naga Venkata Sai Jitin Jami, Thomas Altstidl, Jonas Mueller +4
Random splitting of datasets in image segmentation often leads to unrepresentative test sets, resulting in biased evaluations and poor model generalization. While stratified sampli…
Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers
Lukas Boehm, Jonas Leo Mueller, Christoffer Loeffler +3
Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are…