Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917661554769920 |
|---|---|
| author | Mossina, Luca Dalmau, Joseba andéol, Léo |
| author_facet | Mossina, Luca Dalmau, Joseba andéol, Léo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty Mossina, Luca Dalmau, Joseba andéol, Léo Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2405.05145 |