collaborators

6 papers

cs.CV2026

Mitigating Shortcut Learning: Texture-Penalized Prototype Networks

Akshay Anilkumar Girija, Elena Hoemann, Frank Köster +1

Standard Convolutional Neural Networks (CNNs) exhibit severe performance degradation due to a strong inductive texture bias that prioritizes local, high-frequency patterns over glo…

cs.AI2026

Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems

Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann +2

Artificial Intelligence (AI) offers significant potential for future aviation systems; however, its integration into safety-critical applications requires compliance with the aviat…

cs.AI2026

On the Applicability of Safety Nets: A Safety-By-Design Solution for Certifying Neural Networks

Johann Maximilian Christensen, Thomas Stefani, Elena Hoemann +2

The integration of Artificial Intelligence (AI) in safety-critical aviation systems presents significant challenges for certification and deployment. Aviation, often regarded as th…

cs.CV2026

Image Quality Dependent Degradation for AI Systems

Yannick Kees, Elena Hoemann, Frank Köster +1

Perception is one of the primary applications where neural networks outperform conventional algorithms. One example is AI systems for automated driving, which can detect pedestrian…

cs.AI2026

From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann +2

While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence…

cs.AI2026

Defining Operational Conditions for Safety-Critical AI-Based Systems from Data

Johann Maximilian Christensen, Elena Hoemann, Frank Köster +1

Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the und…