loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Hamed H. Aghdam ; Elnaz J. Heravi and Domenec Puig

Affiliation: Rovira i Virgili University, Spain

Keyword(s): Adversarial Examples, Convolutional Neural Networks, Fourier Transform.

Abstract: Understanding internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating stability of a ConvNet against noise. In this paper, we show how to analyze a ConvNet in the frequency domain. Using the frequency domain analysis, we show the reason that a ConvNet might be sensitive to a very low magnitude additive noise. Our experiments on a few ConvNets trained on different datasets reveals that convolution kernels of a trained ConvNet usually pass most of the frequencies and they are not able to effectively eliminate the effect of high frequencies.They also show that a convolution kernel with more concentrated frequency response is more stable against noise. Finally, we illustrate that augmenting a dataset with noisy images can compress the frequency response of convolution kernels.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.118.149.55

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Aghdam, H.; J. Heravi, E. and Puig, D. (2017). Studying Stability of Different Convolutional Neural Networks Against Additive Noise. In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - Volume 5: VISAPP; ISBN 978-989-758-226-4; ISSN 2184-4321, SciTePress, pages 362-369. DOI: 10.5220/0006200003620369

@conference{visapp17,
author={Hamed H. Aghdam. and Elnaz {J. Heravi}. and Domenec Puig.},
title={Studying Stability of Different Convolutional Neural Networks Against Additive Noise},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - Volume 5: VISAPP},
year={2017},
pages={362-369},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006200003620369},
isbn={978-989-758-226-4},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - Volume 5: VISAPP
TI - Studying Stability of Different Convolutional Neural Networks Against Additive Noise
SN - 978-989-758-226-4
IS - 2184-4321
AU - Aghdam, H.
AU - J. Heravi, E.
AU - Puig, D.
PY - 2017
SP - 362
EP - 369
DO - 10.5220/0006200003620369
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic