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

TL;DR

This paper introduces a cycle consistency-based method for quantifying uncertainty in neural networks solving inverse imaging problems, demonstrating improved detection of data corruption and distribution shifts.

Contribution

It presents a novel, theoretically grounded approach to uncertainty estimation using cycle consistency, applicable across various neural networks in inverse problems.

Findings

Outperforms existing models in detecting unseen data corruption

Effectively identifies distribution shifts in input data

Provides a rapid, universally applicable uncertainty quantification method

Abstract

Uncertainty estimation is critical for numerous applications of deep neural networks and draws growing attention from researchers. Here, we demonstrate an uncertainty quantification approach for deep neural networks used in inverse problems based on cycle consistency. We build forward-backward cycles using the physical forward model available and a trained deep neural network solving the inverse problem at hand, and accordingly derive uncertainty estimators through regression analysis on the consistency of these forward-backward cycles. We theoretically analyze cycle consistency metrics and derive their relationship with respect to uncertainty, bias, and robustness of the neural network inference. To demonstrate the effectiveness of these cycle consistency-based uncertainty estimators, we classified corrupted and out-of-distribution input image data using some of the widely used image deblurring and super-resolution neural networks as testbeds. The blind testing of our method outperformed other models in identifying unseen input data corruption and distribution shifts. This work provides a simple-to-implement and rapid uncertainty quantification method that can be universally applied to various neural networks used for solving inverse problems.