Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

Patrick Knöbelreiter*, Christian Sormann, Alexander Shekhovtsov, Friedrich Fraundorfer, Thomas Pock

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paper

Abstract

It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models. The main difficulties in implementing this in practice are associated with a discrepancy in suitable learning objectives as well as with the necessity of approximations for the inference. In this work we take one of the simplest inference methods, a truncated max-product Belief Propagation, and add what is necessary to make it a proper component of a deep learning model: connect it to learning formulations with losses on marginals and compute the backprop operation. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs), allowing us to design a hierarchical model composing BP inference and CNNs at different scale levels. The model is applicable to a range of dense prediction problems, is well-Trainable and provides parameter-efficient and robust solutions in stereo, flow and semantic segmentation.

Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020
PublisherIEEEXplore
Pages7897-7906
Number of pages10
DOIs
Publication statusPublished - 14 Jun 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2020 - virtuell, Virtual, United States
Duration: 14 Jun 202019 Jun 2020

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2020
CountryUnited States
CityVirtual
Period14/06/2019/06/20

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems'. Together they form a unique fingerprint.

Cite this