Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00342650" target="_blank" >RIV/68407700:21230/20:00342650 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR42600.2020.00792" target="_blank" >https://doi.org/10.1109/CVPR42600.2020.00792</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR42600.2020.00792" target="_blank" >10.1109/CVPR42600.2020.00792</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF18_070%2F0010457" target="_blank" >EF18_070/0010457: Mezinárodní mobility výzkumných pracovníků MSCA-IF II na ČVUT v Praze</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition

ISBN

978-1-7281-7169-2

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

7897-7906

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Seattle

Datum konání akce

13. 6. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—