Neural network uncertainty quantification in inverse imaging problems based on cycle consistency

Luzhe Huang; Jianing Li; Xiaofu Ding; Yijie Zhang; Hanlong Chen; Aydogan Ozcan

doi:10.1117/12.3000686

13 March 2024 Neural network uncertainty quantification in inverse imaging problems based on cycle consistency

Luzhe Huang, Jianing Li, Xiaofu Ding, Yijie Zhang, Hanlong Chen, Aydogan Ozcan

Proceedings Volume PC12903, AI and Optical Data Sciences V; PC129030T (2024) https://doi.org/10.1117/12.3000686
Event: SPIE OPTO, 2024, San Francisco, California, United States

Abstract

We demonstrate a simple yet highly effective uncertainty quantification method for neural networks solving inverse imaging problems. We built forward-backward cycles utilizing the physical forward model and the trained network, derived the relationship of cycle consistency with respect to the robustness, uncertainty and bias of network inference, and obtained uncertainty estimators through regression analysis. An XGBoost classifier based on the uncertainty estimators was trained for out-of-distribution detection using artificial noise-injected images, and it successfully generalized to unseen real-world distribution shifts. Our method was validated on out-of-distribution detection in image deblurring and image super-resolution tasks, outperforming other deep neural network-based models.

Conference Presentation

Citation Download Citation

Luzhe Huang, Jianing Li, Xiaofu Ding, Yijie Zhang, Hanlong Chen, and Aydogan Ozcan "Neural network uncertainty quantification in inverse imaging problems based on cycle consistency", Proc. SPIE PC12903, AI and Optical Data Sciences V, PC129030T (13 March 2024); https://doi.org/10.1117/12.3000686

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available