Identity statement area
Reference TypeConference Proceedings
Last Update2020:
Metadata Last Update2020: administrator
Citation KeyOliveiraPenaBert:2020:CoGrSe
TitleA comparison of graph-based semi-supervised learning for data augmentation
DateNov. 7-10, 2020
Access Date2020, Dec. 04
Number of Files1
Size333 KiB
Context area
Author1 Oliveira, Willian Dihanster G. de
2 Penatti, Otávio A. B.
3 Berton, Lilian
Affiliation1 Federal University of Sao Paulo
2 Samsung R&D Institute
3 Federal University of Sao Paulo
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationVirtual
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2020-10-01 16:55:58 :: -> administrator :: 2020
2020-10-28 20:46:51 :: administrator -> :: 2020
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Document Stagenot transferred
Content TypeExternal Contribution
Tertiary TypeFull Paper
KeywordsImage classification, data augmentation, image transformation, GANs, semi-supervised learning, machine learning.
AbstractIn supervised learning, the algorithm accuracy usually improves with the size of the labeled dataset used for training the classifier. However, in many real-life scenarios, obtaining enough labeled data is costly or even not possible. In many circumstances, Data Augmentation (DA) techniques are usually employed, generating more labeled data for training machine learning algorithms. The common DA techniques are applied to already labeled data, generating simple variations of this data. For example, for image classification, image samples are rotated, cropped, flipped or other operators to generate variations of input image samples, and keeping their original labels. Other options are using Neural Networks algorithms that create new synthetic data or to employ Semi-supervised Learning (SSL) that label existing unlabeled data. In this paper, we perform a comparison among graph-based semi-supervised learning (GSSL) algorithms to augment the labeled dataset. The main advantage of using GSSL is that we can increase the training set by adding non-annotated images to the training set, therefore, we can benefit from the huge amount of unlabeled data available. Experiments are performed on five datasets for recognition of handwritten digits and letters (MNIST and EMINIST), animals (Dogs vs Cats), clothes (MNIST-Fashion) and remote sensing images (Brazilian Coffee Scenes), in which we compare different possibilities for DA, including the GSSL, Generative Adversarial Networks (GANs) and traditional Image Transformations (IT) applied on input labeled data. We also evaluated the impact of such techniques on different convolutional neural networks (CNN). Results indicate that, although all DA techniques performed well, GSSL was more robust to different image properties, presenting less accuracy variation across datasets.
source Directory Content
Sibgrapi2020_ID30.pdf 24/09/2020 16:34 561.9 KiB 
agreement Directory Content
agreement.html 24/09/2020 16:34 1.2 KiB 
Conditions of access and use area
Target Filesibgrapi2020_ID30.pdf
e-Mail (login)
Allied materials area
Next Higher Units8JMKD3MGPEW34M/43G4L9S
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
Description control area