3 papers
cs.CV2025
Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
Boyi Chen, Zhangyu Wang, Fabian Deuser +2
Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in m…
cs.CV2025
Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors
Svetlana Pavlitska, Jamie Robb, Nikolai Polley +2
Realistic adversarial attacks on various camera-based perception tasks of autonomous vehicles have been successfully demonstrated so far. However, only a few works considered attac…
cs.RO2024
Modular Fault Diagnosis Framework for Complex Autonomous Driving Systems
Stefan Orf, Sven Ochs, Jens Doll +4
Fault diagnosis is crucial for complex autonomous mobile systems, especially for modern-day autonomous driving (AD). Different actors, numerous use cases, and complex heterogeneous…