2 papers
cs.LG2026
Reference-Guided Machine Unlearning
Jonas Mirlach, Sonia Laguna, Julia E. Vogt
Machine unlearning aims to remove the influence of specific training data from a model while preserving its general utility. In vision, many approximate unlearning methods pursue t…
cs.CV2025
R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside Perception
Jonas Mirlach, Lei Wan, Andreas Wiedholz +2
In autonomous driving, the integration of roadside perception systems is essential for overcoming occlusion challenges and enhancing the safety of Vulnerable Road Users(VRUs). Whil…