Boltzmann machines and denoising autoencoders for image denoising

Kyung Hyun Cho*

*Corresponding author for this work

    Research output: Contribution to conferencePaperScientificpeer-review

    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
    Publication statusPublished - 1 Jan 2013
    MoE publication typeNot Eligible
    EventInternational Conference on Learning Representations - Scottsdale, United States
    Duration: 2 May 20134 May 2013
    Conference number: 1

    Conference

    ConferenceInternational Conference on Learning Representations
    Abbreviated titleICLR
    CountryUnited States
    CityScottsdale
    Period02/05/201304/05/2013

    Fingerprint Dive into the research topics of 'Boltzmann machines and denoising autoencoders for image denoising'. Together they form a unique fingerprint.

    Cite this