Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling - IRT Saint Exupéry - Institut de Recherche Technologique Accéder directement au contenu
Proceedings/Recueil Des Communications Proceedings of Machine Learning Research Année : 2023

Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling

Résumé

Deploying deep learning models in real-world certified systems requires the ability to provide confidence estimates that accurately reflect their uncertainty. In this paper, we demonstrate the use of the conformal prediction framework to construct reliable and trustworthy predictors for detecting railway signals. Our approach is based on a novel dataset that includes images taken from the perspective of a train operator and state-of-the-art object detectors. We test several conformal approaches and introduce a new method based on conformal risk control. Our findings demonstrate the potential of the conformal prediction framework to evaluate model performance and provide practical guidance for achieving formally guaranteed uncertainty bounds.
Fichier principal
Vignette du fichier
main (1).pdf (3.06 Mo) Télécharger le fichier
main.pdf (3.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04063441 , version 1 (11-04-2023)
hal-04063441 , version 2 (12-04-2023)

Identifiants

Citer

Léo Andéol, Thomas Fel, Florence De Grancey, Luca Mossina. Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. Conformal and Probabilistic Prediction with Applications, Proceedings of Machine Learning Research, 2023. ⟨hal-04063441v2⟩
143 Consultations
207 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More