3 citations · 7 across the 7 of their papers we have counts for
9 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…
Caption-Driven Explorations: Aligning Image and Text Embeddings through Human-Inspired Foveated Vision
Dario Zanca, Andrea Zugarini, Simon Dietz +4
Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we…
Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation
Björn Nieth, Thomas Altstidl, Leo Schwinn +1
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promisi…
How Intermodal Interaction Affects the Performance of Deep Multimodal Fusion for Mixed-Type Time Series
Simon Dietz, Thomas Altstidl, Dario Zanca +2
Mixed-type time series (MTTS) is a bimodal data type that is common in many domains, such as healthcare, finance, environmental monitoring, and social media. It consists of regular…
Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors
Dario Zanca, Andrea Zugarini, Simon Dietz +4
Understanding the mechanisms underlying human attention is a fundamental challenge for both vision science and artificial intelligence. While numerous computational models of free-…
Raising the Bar for Certified Adversarial Robustness with Diffusion Models
Thomas Altstidl, David Dobre, Björn Eskofier +2
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training,…
Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks
Thomas Altstidl, An Nguyen, Leo Schwinn +4
The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant…