Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Abstract

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do not provide uncertainty on the obtained reconstruction. In this work, we develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks. The approach builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic framework. Scalability is achieved by being hybrid in the architecture: only the last layer of each block is Bayesian, while the others remain deterministic, and by being greedy in training. The framework is showcased on one representative medical imaging modality, viz. computed tomography with either sparse view or limited view data, and exhibits competitive performance with respect to state-of-the-art benchmarks, e.g., total variation, deep gradient descent and learned primal-dual.

arXiv comment8 pages, 6 figures

References in corpus (15)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Image reconstruction by domain transform manifold learning
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Weight Uncertainty in Neural Networks
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Variational Dropout and the Local Reparameterization Trick
• Model based learning for accelerated, limited-view 3D photoacoustic tomography
• Practical Deep Learning with Bayesian Principles
• Recurrent Inference Machines for Solving Inverse Problems
• Deep Bayesian Inversion
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• On the Expressiveness of Approximate Inference in Bayesian Neural Networks
• Variational Bayesian dropout: pitfalls and fixes
• Good Initializations of Variational Bayes for Deep Models
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration

Cited by in corpus (3)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• The Modern Mathematics of Deep Learning
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction