<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPEW34M/3U3K5TH</identifier>
		<repository>sid.inpe.br/sibgrapi/2019/09.16.01.10</repository>
		<lastupdate>2019:09.16.01.10.43 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2019/09.16.01.10.43</metadatarepository>
		<metadatalastupdate>2022:06.14.00.09.43 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2019}</metadatalastupdate>
		<doi>10.1109/SIBGRAPI.2019.00025</doi>
		<citationkey>CáceresCondCháv:2019:ExDoCr</citationkey>
		<title>Exploring Double Cross Cyclic Interpolation in Unpaired Image-to-Image Translation</title>
		<format>On-line</format>
		<year>2019</year>
		<numberoffiles>1</numberoffiles>
		<size>2736 KiB</size>
		<author>Cáceres, Jorge Roberto López,</author>
		<author>Condori, Manasses Antoni Mauricio,</author>
		<author>Chávez, Guillermo Cámara,</author>
		<affiliation>Universidad Católica San Pablo</affiliation>
		<affiliation>Universidad Católica San Pablo</affiliation>
		<affiliation>Federal University of Ouro Preto</affiliation>
		<editor>Oliveira, Luciano Rebouças de,</editor>
		<editor>Sarder, Pinaki,</editor>
		<editor>Lage, Marcos,</editor>
		<editor>Sadlo, Filip,</editor>
		<e-mailaddress>manasses.mauricio@ucsp.edu.pe</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 32 (SIBGRAPI)</conferencename>
		<conferencelocation>Rio de Janeiro, RJ, Brazil</conferencelocation>
		<date>28-31 Oct. 2019</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<keywords>Unpaired Image-to-Image Translation, Latent Space Interpolation, Cross-domain Model.</keywords>
		<abstract>The unpaired image-to-image translation consists of transferring a sample $a$ in the domain $A$ to an analog sample $b$ in the domain $B$ without intensive pixel-to-pixel supervision. The current vision focuses on learning a generative function that maps both domains but ignoring the latent information, although its exploration is not explicit supervision. This paper proposes a cross-domain GAN-based model to achieve a bi-directional translation guided by latent space supervision. The proposed architecture provides a double-loop cyclic reconstruction loss in an exchangeable training adopted to reduce mode collapse and enhance local details. Our proposal has outstanding results in visual quality, stability, and pixel-level segmentation metrics over different public datasets.</abstract>
		<language>en</language>
		<targetfile>Sibgrapi19_CycleGAN.pdf</targetfile>
		<usergroup>manasses.mauricio@ucsp.edu.pe</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPEW34M/3UA4FNL</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/3UA4FPS</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2019/10.25.18.30.33 3</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<username>manasses.mauricio@ucsp.edu.pe</username>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2019/09.16.01.10</url>
	</metadata>
</metadatalist>