Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty - IRT Saint Exupéry - Institut de Recherche Technologique
Communication Dans Un Congrès Année : 2024

Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty

Résumé

We propose a post-hoc, computationally lightweight method to quantify predictive uncertainty in semantic image segmentation. Our approach uses conformal prediction to generate statistically valid prediction sets that are guaranteed to include the ground-truth segmentation mask at a predefined confidence level. We introduce a novel visualization technique of conformalized predictions based on heatmaps, and provide metrics to assess their empirical validity. We demonstrate the effectiveness of our approach on well-known benchmark datasets and image segmentation prediction models, and conclude with practical insights.
Fichier principal
Vignette du fichier
cosis_SAIAD_2024_HAL_version.pdf (7.93 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04565173 , version 1 (01-05-2024)

Identifiants

  • HAL Id : hal-04565173 , version 1

Citer

Luca Mossina, Joseba Dalmau, Léo Andéol. Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2024, Seattle, United States. pp.3574-3584. ⟨hal-04565173⟩
199 Consultations
122 Téléchargements

Partager

More