Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift
Evaluating explainable AI reliability for autonomous vehicle perception systems across diverse driving conditions.
Explainability is increasingly required for perception models in intelligent vehicles, yet whether explanations remain faithful under driving domain shift is still poorly understood. This work audits post-hoc explanations of a fixed YOLOv8s pedestrian detector across PIE and JAAD...
ArXiv CS.CV
Source
Generated insight by OnAirToday AI
Ensuring explainability remains consistent under domain shifts is critical for the safety-critical deployment of autonomous vehicles in diverse environments. This research highlights the urgent need for robust auditing frameworks that verify if AI decision-making tools maintain reliability when encountering unseen pedestrian data.

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.