Object Detection With Probabilistic Guarantees
Résumé
Providing reliable uncertainty quantification for complex visual tasks such as object detection is of utmost importance for safety-critical applications such as autonomous driving, tumor detection, etc. Conformal prediction methods offer simple yet practical means to build uncertainty estimations that come with probabilistic guarantees. In this paper we apply such methods to the task of object localization and illustrate our analysis on a pedestrian detection use-case. We highlight both theoretical and practical implications of our analysis.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|