Equivariant Neural Networks for Inverse Problems

Speaker(s) Matthias Ehrhardt University of Bath
Date 29 September 2021 – 11:00 to 11:40
Venue INI Seminar Room 1
Session Title Equivariant Neural Networks for Inverse Problems
Chair Tatiana Alessandra Bubba
Event [MDLW02] Deep learning and inverse problems

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. In this work, we demonstrate that roto-translational equivariant convolutions can improve reconstruction quality compared to standard convolutions when used within a learned reconstruction method. This is almost a free lunch since only little extra computational cost during training and absolutely no extra cost at test time is needed.

Supported By