# Quantification of Predictive Uncertainty via Inference-Time Sampling

arXiv: https://arxiv.org/abs/2308.01731 · HTML: https://mlsanity.com/paper/2308.01731/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/1906.04045/) (2019)
- [Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation](https://mlsanity.com/paper/1705.08302/) (2017)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Generalizing Hamiltonian Monte Carlo with Neural Networks](https://mlsanity.com/paper/1711.09268/) (2017)
- [A-NICE-MC: Adversarial Training for MCMC](https://mlsanity.com/paper/1706.07561/) (2017)
- [MintNet: Building Invertible Neural Networks with Masked Convolutions](https://mlsanity.com/paper/1907.07945/) (2019)
- [Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution](https://mlsanity.com/paper/1705.00664/) (2017)
- [Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel](https://mlsanity.com/paper/1906.00588/) (2019)
- [Probabilistic 3D surface reconstruction from sparse MRI information](https://mlsanity.com/paper/2010.02041/) (2020)
- [Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors](https://mlsanity.com/paper/1807.11272/) (2018)
- [MCMC Shape Sampling for Image Segmentation with Nonparametric Shape Priors](https://mlsanity.com/paper/1611.03749/) (2016)

## Abstract (arXiv)

Predictive variability due to data ambiguities has typically been addressed via construction of dedicated models with built-in probabilistic capabilities that are trained to predict uncertainty estimates as variables of interest. These approaches require distinct architectural components and training mechanisms, may include restrictive assumptions and exhibit overconfidence, i.e., high confidence in imprecise predictions. In this work, we propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions. It is architecture agnostic and can be applied to any feed-forward deterministic network without changes to the architecture or training procedure. Experiments on regression tasks on imaging and non-imaging input data show the method's ability to generate diverse and multi-modal predictive distributions, and a desirable correlation of the estimated uncertainty with the prediction error.