Invert to Learn to Invert
release_tyxhrfx2xfhbfo3pjhec2nhrri
by
Patrick Putzky, Max Welling
2019
Abstract
Iterative learning to infer approaches have become popular solvers for
inverse problems. However, their memory requirements during training grow
linearly with model depth, limiting in practice model expressiveness. In this
work, we propose an iterative inverse model with constant memory that relies on
invertible networks to avoid storing intermediate activations. As a result, the
proposed approach allows us to train models with 400 layers on 3D volumes in an
MRI image reconstruction task. In experiments on a public data set, we
demonstrate that these deeper, and thus more expressive, networks perform
state-of-the-art image reconstruction.
In text/plain
format
Archived Files and Locations
application/pdf 1.7 MB
file_6t2o2kdcqjhifevnppr6fvnhge
|
arxiv.org (repository) web.archive.org (webarchive) |
1911.10914v1
access all versions, variants, and formats of this works (eg, pre-prints)