output
20122026
most citedA Survey on the Explainability of Supervised Machine Learning

984 citations

54 papers

astro-ph.GA2026★ 1 cited

Age and metallicity of the Milky Way's nuclear star cluster studied at 3 pc from Sagittarius A*

E. Gallego-Cano, R. Schödel, T. K. Fritz +5

The Milky Way's nuclear star cluster (NSC) is a unique laboratory to study the formation and evolution of dense stellar systems around a supermassive black hole. Previous work sugg…

cs.CV2026★ 1 cited

Higher-Order Adversarial Patches for Real-Time Object Detectors

Jens Bayer, Stefan Becker, David Münch +2

Higher-order adversarial attacks can directly be considered the result of a cat-and-mouse game -- an elaborate action involving constant pursuit, near captures, and repeated escape…

cs.IT2025

OGC Geotech Interoperability Experiment Engineering Report

Mickaël Beaufils, Katharina Schleidt, Hylke van Der Schaaf +3

This Engineering Report (ER) describes the outcomes of the Open Geospatial Consortium (OGC) Geotech Interoperability Experiment (IE). The objective of this IE was to develop a comm…

cs.RO2025

From Real-World Traffic Data to Relevant Critical Scenarios

Florian Lüttner, Nicole Neis, Daniel Stadler +5

The reliable operation of autonomous vehicles, automated driving functions, and advanced driver assistance systems across a wide range of relevant scenarios is critical for their d…

cs.CV2025★ 1 cited

Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception

Anne Sielemann, Valentin Barner, Stefan Wolf +3

Common approaches to explainable AI (XAI) for deep learning focus on analyzing the importance of input features on the classification task in a given model: saliency methods like S…

cs.CV2025★ 3 cited

Synset Signset Germany: a Synthetic Dataset for German Traffic Sign Recognition

Anne Sielemann, Lena Loercher, Max-Lion Schumacher +3

In this paper, we present a synthesis pipeline and dataset for training / testing data in the task of traffic sign recognition that combines the advantages of data-driven and analy…