Current studentsExisting staffContact us
 

Why are generative adversarial networks so fascinating and annoying?

Simple item page
dc.contributor.authorFaria, F.A.
dc.contributor.authorCarneiro, G.
dc.contributor.conferenceConference on Computer Graphics and Image Processing (SIBGRAPI) (7 Nov 2020 - 10 Nov 2020 : Virtual online)
dc.date.issued2020
dc.description.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).
dc.description.statementofresponsibilityFabio Augusto Faria, Gustavo Carneiro
dc.identifier.citationBrazilian Symposium of Computer Graphic and Image Processing, 2020, pp.1-8
dc.identifier.doi10.1109/SIBGRAPI51738.2020.00009
dc.identifier.isbn9781728192741
dc.identifier.issn1530-1834
dc.identifier.issn2377-5416
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttp://hdl.handle.net/2440/130210
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeonline
dc.relation.ispartofseriesSIBGRAPI - Brazilian Symposium on Computer Graphics and Image Processing
dc.rights©2020 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/9265968/proceeding
dc.titleWhy are generative adversarial networks so fascinating and annoying?
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_130210.pdf
Size:
8.78 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download

Collections

Computer Science publications