Recurrent Inference Machines for Solving Inverse Problems

Abstract

Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and interpreted as a recurrent neural network (RNN) which allows for joint learning of model and inference parameters with back-propagation through time. In this framework, the RNN architecture is directly derived from a hand-chosen inference algorithm, effectively limiting its capabilities. We propose a learning framework, called Recurrent Inference Machines (RIM), in which we turn algorithm construction the other way round: Given data and a task, train an RNN to learn an inference algorithm. Because RNNs are Turing complete [1, 2] they are capable to implement any inference algorithm. The framework allows for an abstraction which removes the need for domain knowledge. We demonstrate in several image restoration experiments that this abstraction is effective, allowing us to achieve state-of-the-art performance on image denoising and super-resolution tasks and superior across-task generalization.

References in corpus (1)

• On learning optimized reaction diffusion processes for effective image restoration

Cited by in corpus (13)

• Learning to solve inverse problems using Wasserstein loss
• Uncertainty Quantification with Generative Models
• i-RIM applied to the fastMRI challenge
• Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems
• Conditional Variational Autoencoder for Learned Image Reconstruction
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction
• Degrees of Freedom Analysis of Unrolled Neural Networks
• Compressive-Sensing Data Reconstruction for Structural Health Monitoring: A Machine-Learning Approach
• R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery
• Recurrent machines for likelihood-free inference
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
• Foreground color prediction through inverse compositing
• Reconstructing unseen modalities and pathology with an efficient Recurrent Inference Machine