3D Shapes Classification Using Intermediate Parts Representation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F22%3A00364177" target="_blank" >RIV/68407700:21730/22:00364177 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-08974-9_34" target="_blank" >https://doi.org/10.1007/978-3-031-08974-9_34</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-08974-9_34" target="_blank" >10.1007/978-3-031-08974-9_34</a>

Jazyk výsledku

angličtina

Název v původním jazyce

3D Shapes Classification Using Intermediate Parts Representation

Popis výsledku v původním jazyce

We describe a novel approach for 3D shape classification which classifies the shape based on a graph of its parts. To segment out the parts of a given object, we train a shape segmentation network to mimic the segments obtained from an offline co-segmentation method. Using the predicted segments, our approach constructs a spatial graph of the parts which reflects the spatial relations between them. The graph of parts is finally classified by a Tensor Field Network - a type of a graph neural network which is designed to be equivariant to rotations and translations. Therefore, the classification of the spatial graph of parts is not influenced by the choice of the coordinate frame. We also introduce a data augmentation method which is particularly suitable to our setting. A preliminary experimental results show that our method is competitive with the standard approach which does not detect parts as an intermediate step. The intermediate representation of parts makes the whole model more interpretable.

Název v anglickém jazyce

3D Shapes Classification Using Intermediate Parts Representation

Popis výsledku anglicky

We describe a novel approach for 3D shape classification which classifies the shape based on a graph of its parts. To segment out the parts of a given object, we train a shape segmentation network to mimic the segments obtained from an offline co-segmentation method. Using the predicted segments, our approach constructs a spatial graph of the parts which reflects the spatial relations between them. The graph of parts is finally classified by a Tensor Field Network - a type of a graph neural network which is designed to be equivariant to rotations and translations. Therefore, the classification of the spatial graph of parts is not influenced by the choice of the coordinate frame. We also introduce a data augmentation method which is particularly suitable to our setting. A preliminary experimental results show that our method is competitive with the standard approach which does not detect parts as an intermediate step. The intermediate representation of parts makes the whole model more interpretable.

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/LL1902" target="_blank" >LL1902: Obohacování SMT řešičů pomocí strojového učení</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Information Processing and Management of Uncertainty in Knowledge-Based Systems

ISBN

978-3-031-08973-2

ISSN

1865-0929

e-ISSN

1865-0929

Počet stran výsledku

12

Strana od-do

431-442

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Miláno

Datum konání akce

11. 7. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—