DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ko, Minsu | ko |
dc.contributor.author | Cha, Eunju | ko |
dc.contributor.author | Suh, Sungjoo | ko |
dc.contributor.author | Lee, Huijin | ko |
dc.contributor.author | Han, Jae-Joon | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.contributor.author | Han, Bohyung | ko |
dc.date.accessioned | 2023-03-28T06:00:27Z | - |
dc.date.available | 2023-03-28T06:00:27Z | - |
dc.date.created | 2023-03-08 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.18280 - 18289 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/305866 | - |
dc.description.abstract | Unsupervised image-to-image translation has gained considerable attention due to recent impressive advances in generative adversarial networks (GANs). This paper presents a simple but effective regularization technique for improving GAN-based image-to-image translation. To generate images with realistic local semantics and structures, we propose an auxiliary self-supervision loss that enforces point-wise consistency of the overlapping region between a pair of patches cropped from a single real image during training the discriminator of a GAN. Our experiment shows that the proposed dense consistency regularization improves performance substantially on various image-to-image translation scenarios. It also leads to extra performance gains through the combination with instance-level regularization methods. Furthermore, we verify that the proposed model captures domain-specific characteristics more effectively with only a small fraction of training data. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Self-Supervised Dense Consistency Regularization for Image-to-Image Translation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000870783004011 | - |
dc.identifier.scopusid | 2-s2.0-85137654364 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 18280 | - |
dc.citation.endingpage | 18289 | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | New Orleans, LA | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.01776 | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
dc.contributor.nonIdAuthor | Ko, Minsu | - |
dc.contributor.nonIdAuthor | Cha, Eunju | - |
dc.contributor.nonIdAuthor | Suh, Sungjoo | - |
dc.contributor.nonIdAuthor | Lee, Huijin | - |
dc.contributor.nonIdAuthor | Han, Jae-Joon | - |
dc.contributor.nonIdAuthor | Han, Bohyung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.