CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition

ICLR 2026 Conference Submission16852 Authors

Keywords: Conformal prediction, Uncertainty quantification, Image segmentation

TL;DR: We developed a conformal prediction strategy for image segmentation that accounts for spatial correlation to achieve improved results

Abstract:

Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model’s predicted probability for each class label at every pixel. While this information can be particularly valuable in high-stakes domains such as medical imaging, these scores are heuristic in nature and do not constitute rigorous quantitative uncertainty estimates.
Conformal prediction (CP) provides a principled framework for transforming heuristic confidence scores into statistically valid uncertainty estimates. However, applying CP directly to image segmentation ignores the spatial correlations between pixels, a fundamental characteristic of image data. This can result in overly conservative and less interpretable uncertainty estimates.
To address this, we propose CONSIGN (*Conformal Segmentation Informed by Spatial Groupings via Decomposition*), a CP-based method that incorporates spatial correlations to improve uncertainty quantification in image segmentation.
Our method generates meaningful prediction sets that come with user-specified, high-probability error guarantees.
It is compatible with any pre-trained segmentation model capable of generating multiple sample outputs.
We evaluate CONSIGN against two CP baselines across three medical imaging datasets and two COCO dataset subsets, using three different pre-trained segmentation models. Results demonstrate that accounting for spatial structure significantly improves performance across multiple metrics and enhances the quality of uncertainty estimates.

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

Submission Number: 16852