Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/43BFBQE
Repositorysid.inpe.br/sibgrapi/2020/09.30.13.05
Last Update2020:09.30.13.05.44 ffaria@unifesp.br
Metadatasid.inpe.br/sibgrapi/2020/09.30.13.05.44
Metadata Last Update2020:10.28.20.46.59 administrator
Citation KeyFariaCarn:2020:WhArGe
TitleWhy are Generative Adversarial Networks so Fascinating and Annoying?
FormatOn-line
Year2020
Access Date2021, June 18
Number of Files1
Size8634 KiB
Context area
Author1 Faria, Fabio Augusto
2 Carneiro, Gustavo
Affiliation1 Universidade Federal de São Paulo
2 The University of Adelaide
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addressffaria@unifesp.br
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationVirtual
DateNov. 7-10, 2020
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeTutorial
History2020-09-30 13:05:44 :: ffaria@unifesp.br -> administrator ::
2020-10-28 20:46:59 :: administrator -> ffaria@unifesp.br :: 2020
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
KeywordsGAN, machine learning, computer vision, deep learning.
AbstractThis paper focuses on one of the most fascinating and successful, but challenging generative models in the literature: the Generative Adversarial Networks (GAN). Recently, GAN has attracted much attention by the scientific community and the entertainment industry due to its effectiveness in generating complex and high-dimension data, which makes it a superior model for producing new samples, compared with other types of generative models. The traditional GAN (referred to as the Vanilla GAN) is composed of two neural networks, a generator and a discriminator, which are modeled using a minimax optimization. The generator creates samples to fool the discriminator that in turn tries to distinguish between the original and created samples. This optimization aims to train a model that can generate samples from the training set distribution. In addition to defining and explaining the Vanilla GAN and its main variations (e.g., DCGAN, WGAN, and SAGAN), this paper will present several applications that make GAN an extremely exciting method for the entertainment industry (e.g., style-transfer and image-to-image translation). Finally, the following measures to assess the quality of generated images are presented: Inception Search (IS), and Frechet Inception Distance (FID).
Arrangementurlib.net > SDLA > SIBGRAPI 2020 > Why are Generative...
source Directory Contentthere are no files
agreement Directory Content
agreement.html 30/09/2020 10:05 1.2 KiB 
Conditions of access and use area
data URLhttp://urlib.net/rep/8JMKD3MGPEW34M/43BFBQE
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/43BFBQE
Languageen
Target FileGAN_Tutorial_SIBGRAPI2020.pdf
User Groupffaria@unifesp.br
Visibilityshown
Update Permissionnot transferred
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/43G4L9S
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
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
e-Mail (login)ffaria@unifesp.br
update 

Close