Invert to Learn to Invert release_tyxhrfx2xfhbfo3pjhec2nhrri

by Patrick Putzky, Max Welling

Released as a article .

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)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-11-25
Version   v1
Language   en ?
arXiv  1911.10914v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 4cb4fe08-ade2-4f15-9e16-3b2d4d38e27c
API URL: JSON