3D Capsule Networks for Object Classification from 3D Model Data

Ayesha Ahmad, Burak Kakillioglu, Senem Velipasalar

Research output: Chapter in Book/Entry/PoemConference contribution

16 Scopus citations

Abstract

Many of the existing object classification methods today rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot sufficiently address the spatial relationship between features and require large amounts of data for training. In this paper, a new architecture is proposed for 3D object classification, which is an extension of the Capsule Networks (CapsNets) to 3D data. Our proposed 3D CapsNet architecture preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We compare our approach with a ShapeNet inspired model, and show that our method provides performance improvement especially when training data size gets smaller. We also compare and evaluate several different versions of the 3D Capsnet architecture.

Original languageEnglish (US)
Title of host publicationConference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages2225-2229
Number of pages5
ISBN (Electronic)9781538692189
DOIs
StatePublished - Jul 2 2018
Event52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States
Duration: Oct 28 2018Oct 31 2018

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2018-October
ISSN (Print)1058-6393

Conference

Conference52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
Country/TerritoryUnited States
CityPacific Grove
Period10/28/1810/31/18

Keywords

  • 3D
  • Capsule networks
  • object classification

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of '3D Capsule Networks for Object Classification from 3D Model Data'. Together they form a unique fingerprint.

Cite this