6 papers
LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving
Mert Keser, Alois Knoll
Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Introspection methods that predi…
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein +9
Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this…
Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods
Kumar Manas, Mert Keser, Alois Knoll
This survey provides an analysis of current methodologies integrating legal and logical specifications into the perception, prediction, and planning modules of automated driving sy…
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
Gesina Schwalbe, Georgii Mikriukov, Edgar Heinert +5
The thriving research field of concept-based explainable artificial intelligence (C-XAI) investigates how human-interpretable semantic concepts embed in the latent spaces of deep n…
Unveiling Ontological Commitment in Multi-Modal Foundation Models
Mert Keser, Gesina Schwalbe, Niki Amini-Naieni +2
Ontological commitment, i.e., used concepts, relations, and assumptions, are a corner stone of qualitative reasoning (QR) models. The state-of-the-art for processing raw inputs, th…
How Could Generative AI Support Compliance with the EU AI Act? A Review for Safe Automated Driving Perception
Mert Keser, Youssef Shoeb, Alois Knoll
Deep Neural Networks (DNNs) have become central for the perception functions of autonomous vehicles, substantially enhancing their ability to understand and interpret the environme…