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

Abstract

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.

Cite

Text

Mossina et al. "Conformal Semantic Image Segmentation: Post-Hoc Quantification of Predictive Uncertainty." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00361

Markdown

[Mossina et al. "Conformal Semantic Image Segmentation: Post-Hoc Quantification of Predictive Uncertainty." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/mossina2024cvprw-conformal/) doi:10.1109/CVPRW63382.2024.00361

BibTeX

@inproceedings{mossina2024cvprw-conformal,
  title     = {{Conformal Semantic Image Segmentation: Post-Hoc Quantification of Predictive Uncertainty}},
  author    = {Mossina, Luca and Dalmau, Joseba and Andéol, Léo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2024},
  pages     = {3574-3584},
  doi       = {10.1109/CVPRW63382.2024.00361},
  url       = {https://mlanthology.org/cvprw/2024/mossina2024cvprw-conformal/}
}