Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks

In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the lo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer graphics forum Ročník 34; číslo 5; s. 13 - 23
Hlavní autoři: Boscaini, D., Masci, J., Melzi, S., Bronstein, M. M., Castellani, U., Vandergheynst, P.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Blackwell Publishing Ltd 01.08.2015
Témata:
Analysis
Categories and Subject Descriptors (according to ACM CCS)
Computational Geometry and Object Modeling [I.3.5]
Computer graphics
Cost engineering
Deformation
Feature Measurement [I.4.7]
Formability
Fourier transforms
Learning
Learning [I.2.6]
Networks
Neural networks
Spectra
State of the art
Studies
Topological manifolds
ISSN:0167-7055, 1467-8659
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we propose a generalization of convolutional neural networks (CNN) to non‐Euclidean domains for the analysis of deformable shapes. Our construction is based on localized frequency analysis (a generalization of the windowed Fourier transform to manifolds) that is used to extract the local behavior of some dense intrinsic descriptor, roughly acting as an analogy to patches in images. The resulting local frequency representations are then passed through a bank of filters whose coefficient are determined by a learning procedure minimizing a task‐specific cost. Our approach generalizes several previous methods such as HKS, WKS, spectral CNN, and GPS embeddings. Experimental results show that the proposed approach allows learning class‐specific shape descriptors significantly outperforming recent state‐of‐the‐art methods on standard benchmarks.
Bibliografie:istex:A9D816B10CB68EF9EA6AD9D2E557CB4334DA3231
ark:/67375/WNG-TC3RFCKJ-S
ArticleID:CGF12693
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12693