
How Do You Act? An Empirical Study to Understand Behavior of Deep Reinforcement Learning Agents
The demand for more transparency of decisionmaking processes of deep re...
read it

Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities
We present a method that "meta" classifies whether segments (objects) pr...
read it

TimeDynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
In the semantic segmentation of street scenes, the reliability of a pred...
read it

Wayfinding and cognitive maps for pedestrian models
Usually, routing models in pedestrian dynamics assume that agents have f...
read it

Deep Bayesian Active SemiSupervised Learning
In many applications the process of generating label information is expe...
read it

Classification Uncertainty of Deep Neural Networks Based on Gradient Information
We study the quantification of uncertainty of Convolutional Neural Netwo...
read it

Exploring ParallelinTime Approaches for Eddy Current Problems
We consider the usage of parallelintime algorithms of the Parareal and...
read it

Using adjoint CFD to quantify the impact of manufacturing variations on a heavy duty turbine vane
We consider the evaluation of manufacturing variations to the aerodynami...
read it

Multigridreductionintime for Eddy Current problems
Parallelintime methods have shown success for reducing the simulation ...
read it

A Statistical Defense Approach for Detecting Adversarial Examples
Adversarial examples are maliciously modified inputs created to fool dee...
read it

A Darwin Time Domain Scheme for the Simulation of Transient Quasistatic Electromagnetic Fields Including Resistive, Capacitive and Inductive Effects
The Darwin field model addresses an approximation to Maxwell's equations...
read it

A simple and efficient dichotomic search algorithm for multiobjective mixed integer linear programs
We present a simple and at the same time fficient algorithm to compute a...
read it

Detection of False Positive and False Negative Samples in Semantic Segmentation
In recent years, deep learning methods have outperformed other methods i...
read it

Inter/extrapolationbased multirate schemes – a dynamiciteration perspective
Multirate behavior of ordinary differential equations (ODEs) and differe...
read it

Discovering Mathematical Objects of Interest – A Study of Mathematical Notations
Mathematical notation, i.e., the writing system used to communicate conc...
read it

Fast Lidar Clustering by Density and Connectivity
Lidar sensors are widely used in various applications, ranging from scie...
read it

Mathematical Formulae in Wikimedia Projects 2020
This poster summarizes our contributions to Wikimedia's processing pipel...
read it

Pairwise MultiClass Document Classification for Semantic Relations between Wikipedia Articles
Many digital libraries recommend literature to their users considering t...
read it

Maximum Entropy Snapshot Sampling for Reduced Basis Generation
Snapshot backended reduced basis methods for dynamical systems commonly...
read it

Towards NLPsupported Semantic Data Management
The heterogeneity of data poses a great challenge when data from differe...
read it

Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language
In this paper, we show how selecting and combining encodings of natural ...
read it

On the Robustness of Active Learning
Active Learning is concerned with the question of how to identify the mo...
read it

Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances
Object detection algorithms for Lidar data have seen numerous publicatio...
read it

A Convenient Infinite Dimensional Framework for Generative Adversarial Learning
In recent years, generative adversarial networks (GANs) have demonstrate...
read it

A TwoStep Darwin Model Time Domain Formulation for Quasistatic Electromagnetic Field Calculations
In the absence of wave propagation, transient electromagnetic fields are...
read it

Fast Linking of Mathematical Wikidata Entities in Wikipedia Articles Using Annotation Recommendation
Mathematical information retrieval (MathIR) applications such as semanti...
read it

False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
Instance segmentation of images is an important tool for automated scene...
read it

GradientBased Quantification of Epistemic Uncertainty for Deep Object Detectors
Reliable epistemic uncertainty estimation is an essential component for ...
read it

Symbol Based Convergence Analysis in Block Multigrid Methods with applications for Stokes problems
The main focus of this paper is the study of efficient multigrid methods...
read it

A Multilevel Approach to Variance Reduction in the Stochastic Estimation of the Trace of a Matrix
The trace of a matrix function f(A), most notably of the matrix inverse,...
read it

Towards Explaining STEM Document Classification using Mathematical Entity Linking
Document subject classification is essential for structuring (digital) l...
read it

A Qualitative Evaluation of User Preference for Linkbased vs. Textbased Recommendations of Wikipedia Articles
Literature recommendation systems (LRS) assist readers in the discovery ...
read it

How to Effectively Identify and Communicate PersonTargeting Media Bias in Daily News Consumption?
Slanted news coverage strongly affects public opinion. This is especiall...
read it

False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation
We present a novel postprocessing tool for semantic segmentation of LiD...
read it

Testing the Generalization of Neural Language Models for COVID19 Misinformation Detection
A drastic rise in potentially lifethreatening misinformation has been a...
read it
Bergische Universität Wuppertal
The Bergische Universität Wuppertal is a dynamic and futureoriented university in the heart of Europe.