Boltzmann machines and denoising autoencoders for image denoising: International Conference on Learning Representations, ICLR 2013

Research output: Contribution to conferencePaper

Abstract

Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.

Original languageEnglish (US)
StatePublished - Jan 1 2013
Event1st International Conference on Learning Representations, ICLR 2013 - Scottsdale, United States
Duration: May 2 2013May 4 2013

Conference

Conference1st International Conference on Learning Representations, ICLR 2013
CountryUnited States
CityScottsdale
Period5/2/135/4/13

Fingerprint

Image denoising
learning
experiment
Experiments
Ludwig Boltzmann
performance

ASJC Scopus subject areas

  • Education
  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Cite this

Cho, K. (2013). Boltzmann machines and denoising autoencoders for image denoising: International Conference on Learning Representations, ICLR 2013. Paper presented at 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, United States.

Boltzmann machines and denoising autoencoders for image denoising : International Conference on Learning Representations, ICLR 2013. / Cho, Kyunghyun.

2013. Paper presented at 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, United States.

Research output: Contribution to conferencePaper

Cho, K 2013, 'Boltzmann machines and denoising autoencoders for image denoising: International Conference on Learning Representations, ICLR 2013' Paper presented at 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, United States, 5/2/13 - 5/4/13, .
Cho K. Boltzmann machines and denoising autoencoders for image denoising: International Conference on Learning Representations, ICLR 2013. 2013. Paper presented at 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, United States.
Cho, Kyunghyun. / Boltzmann machines and denoising autoencoders for image denoising : International Conference on Learning Representations, ICLR 2013. Paper presented at 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, United States.
@conference{3944b6ada8e04d6ead447c6d254ab7f4,
title = "Boltzmann machines and denoising autoencoders for image denoising: International Conference on Learning Representations, ICLR 2013",
abstract = "Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.",
author = "Kyunghyun Cho",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
note = "1st International Conference on Learning Representations, ICLR 2013 ; Conference date: 02-05-2013 Through 04-05-2013",

}

TY - CONF

T1 - Boltzmann machines and denoising autoencoders for image denoising

T2 - International Conference on Learning Representations, ICLR 2013

AU - Cho, Kyunghyun

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.

AB - Image denoising based on a probabilistic model of local image patches has been employed by various researchers, and recently a deep (denoising) autoencoder has been proposed by Burger et al. [2012] and Xie et al. [2012] as a good model for this. In this paper, we propose that another popular family of models in the field of deep learning, called Boltzmann machines, can perform image denoising as well as, or in certain cases of high level of noise, better than denoising autoencoders. We empirically evaluate the two models on three different sets of images with different types and levels of noise. Throughout the experiments we also examine the effect of the depth of the models. The experiments confirmed our claim and revealed that the performance can be improved by adding more hidden layers, especially when the level of noise is high.

UR - http://www.scopus.com/inward/record.url?scp=85070889042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070889042&partnerID=8YFLogxK

M3 - Paper

ER -