Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging

Image-to-image regression is an important learning task, used frequently in biological imaging. Current algorithms, however, do not generally offer statistical guarantees that protect against a model's mistakes and hallucinations. To address this, we develop uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems. In particular, we show how to derive uncertainty intervals around each pixel that are guaranteed to contain the true value with a user-specified confidence probability. Our methods work in conjunction with any base machine learning model, such as a neural network, and endow it with formal mathematical guarantees – regardless of the true unknown data distribution or choice of model. Furthermore, they are simple to implement and computationally inexpensive. We evaluate our procedure on three image-to-image regression tasks: quantitative phase microscopy, accelerated magnetic resonance imaging, and super-resolution transmission electron microscopy of a Drosophila melanogaster brain.


page 2

page 8

page 11


What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems

Estimating uncertainty in image-to-image networks is an important task, ...

Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems

Uncertainty quantification for inverse problems in imaging has drawn muc...

Uncertainty quantification for sparse Fourier recovery

One of the most prominent methods for uncertainty quantification in high...

Cycle Consistency-based Uncertainty Quantification of Neural Networks in Inverse Imaging Problems

Uncertainty estimation is critical for numerous applications of deep neu...

Conffusion: Confidence Intervals for Diffusion Models

Diffusion models have become the go-to method for many generative tasks,...

A Data-Driven Approach for Bayesian Uncertainty Quantification in Imaging

Uncertainty quantification in image restoration is a prominent challenge...

Code Repositories


Image-to-image regression with uncertainty quantification in PyTorch. Take any dataset and train a model to regress images to images with rigorous, distribution-free uncertainty quantification.

view repo

Please sign up or login with your details

Forgot password? Click here to reset