[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Hamed Habibi Aghdam ; Elnaz Jahani Heravi and Domenec Puig

Affiliation: Rovira i Virgili University, Spain

Keyword(s): Convolutional Neural Network, Deep Learning, Object Recognition.

Abstract: Understanding the underlying process of Convolutional Neural Networks (ConvNets) is usually done through visualization techniques. However, these techniques do not provide accurate information about the stability of ConvNets. In this paper, our aim is to analyze the stability of ConvNets through different techniques. First, we propose a new method for finding the minimum noisy image which is located in the minimum distance from the decision boundary but it is misclassified by its ConvNet. Second, we exploratorly and quanitatively analyze the stability of the ConvNets trained on the CIFAR10, the MNIST and the GTSRB datasets. We observe that the ConvNets might make mistakes by adding a Gaussian noise with s = 1 (barely perceivable by human eyes) to the clean image. This suggests that the inter-class margin of the feature space obtained from a ConvNet is slim. Our second founding is that augmenting the clean dataset with many noisy images does not increase the inter-class margin. Conseq uently, a ConvNet trained on a dataset augmented with noisy images might incorrectly classify the images degraded with a low magnitude noise. The third founding reveals that even though an ensemble improves the stability, its performance is considerably reduced by a noisy dataset. (More)

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 79.170.44.78

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:
Habibi Aghdam, H., Jahani Heravi, E. and Puig, D. (2016). Analyzing the Stability of Convolutional Neural Networks against Image Degradation. In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP; ISBN 978-989-758-175-5; ISSN 2184-4321, SciTePress, pages 370-382. DOI: 10.5220/0005720703700382

@conference{visapp16,
author={Hamed {Habibi Aghdam} and Elnaz {Jahani Heravi} and Domenec Puig},
title={Analyzing the Stability of Convolutional Neural Networks against Image Degradation},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP},
year={2016},
pages={370-382},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005720703700382},
isbn={978-989-758-175-5},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP
TI - Analyzing the Stability of Convolutional Neural Networks against Image Degradation
SN - 978-989-758-175-5
IS - 2184-4321
AU - Habibi Aghdam, H.
AU - Jahani Heravi, E.
AU - Puig, D.
PY - 2016
SP - 370
EP - 382
DO - 10.5220/0005720703700382
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

<style> #socialicons>a span { top: 0px; left: -100%; -webkit-transition: all 0.3s ease; -moz-transition: all 0.3s ease-in-out; -o-transition: all 0.3s ease-in-out; -ms-transition: all 0.3s ease-in-out; transition: all 0.3s ease-in-out;} #socialicons>ahover div{left: 0px;} </style>