Equivariant neural networks for inverse problems

Abstract

In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into incorporating other symmetries into deep learning methods, in the form of group equivariant convolutional neural networks. Much of this work has been focused on roto-translational symmetry of ${\mathbf{R}}^d$, but other examples are the scaling symmetry of ${\mathbf{R}}^d$ and rotational symmetry of the sphere. In this work, we demonstrate that group equivariant convolutional operations can naturally be incorporated into learned reconstruction methods for inverse problems that are motivated by the variational regularisation approach. Indeed, if the regularisation functional is invariant under a group symmetry, the corresponding proximal operator will satisfy an equivariance property with respect to the same group symmetry. As a result of this observation, we design learned iterative methods in which the proximal operators are modelled as group equivariant convolutional neural networks. We use roto-translationally equivariant operations in the proposed methodology and apply it to the problems of low-dose computerised tomography reconstruction and subsampled magnetic resonance imaging reconstruction. The proposed methodology is demonstrated to improve the reconstruction quality of a learned reconstruction method with a little extra computational cost at training time but without any extra cost at test time.

References in corpus (14)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• scikit-image: Image processing in Python
• Language Models are Few-Shot Learners
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Learned Primal-dual Reconstruction
• Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
• Group Equivariant Convolutional Networks
• Solving ill-posed inverse problems using iterative deep neural networks
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• General $E(2)$-Equivariant Steerable CNNs
• Recurrent Inference Machines for Solving Inverse Problems
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• Deep Scale-spaces: Equivariance Over Scale