Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Disjunctive Normal Shape Boltzmann Machine

Abstract: 

Shape Boltzmann machine (a type of Deep Boltzmann machine) is a powerful tool for shape modelling; however, has some drawbacks in representation of local shape parts. Disjunctive Normal Shape Model (DNSM) is a strong shape model that can effectively represent local parts of objects. In this paper, we propose a new shape model based on Shape Boltzmann Machine and Disjunctive Normal Shape Model which we call Disjunctive Normal Shape Boltzmann Machine (DNSBM). DNSBM learns binary distributions of shapes by taking both local and global shape constraints into account using a type of Deep Boltzmann Machine. The samples generated using DNSBM look realistic. Moreover, DNSBM is capable of generating novel samples that differ from training examples by exploiting the local shape representation capability of DNSM. We demonstrate the performance of DNSBM for shape completion on two different data sets in which exploitation of local shape parts is important for capturing the statistical variability of the underlying shape distributions. Experimental results show that DNSBM is a strong model for representing shapes that are composed of local parts.

up
0 users have voted:

Paper Details

Authors:
Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin
Submitted On:
13 March 2017 - 3:59pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Ertunc Erdil
Paper Code:
2357
Document Year:
2017
Cite

Document Files

erdil_ICASSP17_presentation.pdf

(102 downloads)

Subscribe

[1] Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin, "Disjunctive Normal Shape Boltzmann Machine", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1760. Accessed: Dec. 17, 2017.
@article{1760-17,
url = {http://sigport.org/1760},
author = {Ertunc Erdil; Fitsum Mesadi; Tolga Tasdizen; Mujdat Cetin },
publisher = {IEEE SigPort},
title = {Disjunctive Normal Shape Boltzmann Machine},
year = {2017} }
TY - EJOUR
T1 - Disjunctive Normal Shape Boltzmann Machine
AU - Ertunc Erdil; Fitsum Mesadi; Tolga Tasdizen; Mujdat Cetin
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1760
ER -
Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin. (2017). Disjunctive Normal Shape Boltzmann Machine. IEEE SigPort. http://sigport.org/1760
Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin, 2017. Disjunctive Normal Shape Boltzmann Machine. Available at: http://sigport.org/1760.
Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin. (2017). "Disjunctive Normal Shape Boltzmann Machine." Web.
1. Ertunc Erdil, Fitsum Mesadi, Tolga Tasdizen, Mujdat Cetin. Disjunctive Normal Shape Boltzmann Machine [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1760