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

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 confid...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 3574 - 3584
Main Authors Mossina, Luca, Dalmau, Joseba, Andeol, Leo
Format Conference Proceeding
LanguageEnglish
Published IEEE 17.06.2024
Subjects
Computational modeling
conformal prediction
Image segmentation
Pedestrians
Predictive models
semantic image segmentation
Semantics
Streaming media
Uncertainty
uncertainty quantification
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2160-7516
DOI:10.1109/CVPRW63382.2024.00361