318 citations · 1k across the 84 of their papers we have counts for
6 papers · 1 filter
Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications
Marion Neumeier, Andreas Tollkühn, Sebastian Dorn +2
For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding.…
A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction
Marion Neumeier, Andreas Tollkühn, Michael Botsch +1
This work introduces the multidimensional Graph Fourier Transformation Neural Network (GFTNN) for long-term trajectory predictions on highways. Similar to Graph Neural Networks (GN…
On Learning the Tail Quantiles of Driving Behavior Distributions via Quantile Regression and Flows
Jia Yu Tee, Oliver De Candido, Wolfgang Utschick +1
Towards safe autonomous driving (AD), we consider the problem of learning models that accurately capture the diversity and tail quantiles of human driver behavior probability distr…
Gradient Derivation for Learnable Parameters in Graph Attention Networks
Marion Neumeier, Andreas Tollkühn, Sebastian Dorn +2
This work provides a comprehensive derivation of the parameter gradients for GATv2 [4], a widely used implementation of Graph Attention Networks (GATs). GATs have proven to be powe…
Classification and Uncertainty Quantification of Corrupted Data using Semi-Supervised Autoencoders
Philipp Joppich, Sebastian Dorn, Oliver De Candido +2
Parametric and non-parametric classifiers often have to deal with real-world data, where corruptions like noise, occlusions, and blur are unavoidable - posing significant challenge…
An Entropy Based Outlier Score and its Application to Novelty Detection for Road Infrastructure Images
Jonas Wurst, Alberto Flores Fernández, Michael Botsch +1
A novel unsupervised outlier score, which can be embedded into graph based dimensionality reduction techniques, is presented in this work. The score uses the directed nearest neigh…