Investigating the effect of loss functions on single-image GAN performance

Basit Öğe Kaydı
dc.contributor.authorYıldız, Eyyüp
dc.contributor.authorYüksel, Erkan
dc.contributor.authorSevgen, Selçuk
dc.date.accessioned2026-02-08T15:04:47Z
dc.date.available2026-02-08T15:04:47Z
dc.date.issued2024
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractLoss functions are crucial in training generative adversarial networks (GANs) and shaping the resulting outputs. These functions, specifically designed for GANs, optimize generator and discriminator networks together but in opposite directions. GAN models, which typically handle large datasets, have been successful in the field of deep learning. However, exploring the factors that influence the success of GAN models developed for limited data problems is an important area of research. In this study, we conducted a comprehensive investigation into the loss functions commonly used in GAN literature, such as binary cross entropy (BCE), Wasserstein generative adversarial network (WGAN), least squares generative adversarial network (LSGAN), and hinge loss. Our research focused on examining the impact of these loss functions on improving output quality and ensuring training convergence in single-image GANs. Specifically, we evaluated the performance of a single-image GAN model, SinGAN, using these loss functions in terms of image quality and diversity. Our experimental results demonstrated that loss functions successfully produce high-quality, diverse images from a single training image. Additionally, we found that the WGAN-GP and LSGAN-GP loss functions are more effective for single-image GAN models.
dc.identifier.doi10.38088/jise.1497968
dc.identifier.endpage225
dc.identifier.issn2602-4217
dc.identifier.issue2
dc.identifier.startpage213
dc.identifier.urihttps://doi.org/10.38088/jise.1497968
dc.identifier.urihttps://hdl.handle.net/20.500.12885/4174
dc.identifier.volume8
dc.language.isoen
dc.publisherBursa Teknik Üniversitesi
dc.relation.ispartofJournal of Innovative Science and Engineering
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_DergiPark_20260207
dc.subjectComputer Vision
dc.subjectBilgisayar Görüşü [EN] Pattern Recognition
dc.subjectÖrüntü Tanıma [EN] Deep Learning
dc.subjectDerin Öğrenme [EN] Neural Networks
dc.subjectNöral Ağlar [EN] Machine Learning (Other)
dc.subjectMakine Öğrenme (Diğer)
dc.titleInvestigating the effect of loss functions on single-image GAN performance
dc.typeArticle

Dosyalar

Koleksiyon

Journal of Innovative Science and Engineering Koleksiyonu