No Cover Image

Conference contribution 231 views 4 downloads

A Deep Convolutional Auto-Encoder with Embedded Clustering / A. Alqahtani; X. Xie; J. Deng; M.W. Jones

2018 25th IEEE International Conference on Image Processing (ICIP), Pages: 4058 - 4062

Swansea University Author: Xie, Xianghua

  • post-publication-revision.pdf

    PDF | Accepted Manuscript

    © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

    Download (295.07KB)

Abstract

We present a graph-based convolutional autoencoder and assess the contribution of four components towards encoding quality. A graph-based convolution-operator is used to learn localised filtering operations for graph-wise encoding. An evaluation of the proposed method is provided on a topologically-...

Full description

Published in: 2018 25th IEEE International Conference on Image Processing (ICIP)
ISBN: 978-1-4799-7062-9 978-1-4799-7061-2
ISSN: 2381-8549
Published: Athens, Greece 2018 IEEE International Conference on Image Processing 2018
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa40805
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: We present a graph-based convolutional autoencoder and assess the contribution of four components towards encoding quality. A graph-based convolution-operator is used to learn localised filtering operations for graph-wise encoding. An evaluation of the proposed method is provided on a topologically-irregular version of MNIST that violates the assumption made by conventional convolutional autoencoder methods of the structure of its input-data.
Keywords: Graph learning, deep learning, autoencoder, irregular domain learning
College: College of Science
Start Page: 4058
End Page: 4062