Cycle Consistency-based Uncertainty Quantification of Neural Networks in Inverse Imaging Problems
arXiv:2305.12852 · doi:10.34133/icomputing.0071
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.
arXiv comment28 Pages, 4 Figures, 1 Table
References in corpus (19)
- XGBoost: A Scalable Tree Boosting System
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Diffusion Models Beat GANs on Image Synthesis
- A Survey of Deep Learning Techniques for Autonomous Driving
- Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
- Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue
- Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
- Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
- Generalized Out-of-Distribution Detection: A Survey
- Reliable deep-learning-based phase imaging with uncertainty quantification
- Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue
- Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology
- Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
- Unsolved Problems in ML Safety
- Single-shot autofocusing of microscopy images using deep learning
- Intriguing Findings of Frequency Selection for Image Deblurring
- eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging
- Variational Inference for Computational Imaging Inverse Problems
- An E-PINN assisted practical uncertainty quantification for inverse problems