Publicación:
Detecting overfitting in GANs with a metric based on the Fourier spectrum

Vista sencilla de ítem
dc.contributor.authorGamazo Tejero, Ángel Javier
dc.contributor.directorRincón Zamorano, Mariano
dc.contributor.directorCuadra Troncoso, José Manuel
dc.date.accessioned2024-05-20T12:23:43Z
dc.date.available2024-05-20T12:23:43Z
dc.date.issued2020-09-28
dc.description.abstractRecent progress in generative image modeling is leading to a new era of highresolution fakes visually indistinguishable from real life images. However, the development of metrics capable of discerning whether images are synthetic or not runs behind the race of achieving the best generator, thus bringing potential threats. We propose a rotation invariant metric capable of distinguishing real and generated images and prove its performance and correlation with subjective evaluation on a brain MRI dataset to generate synthetic white matter lesion images. We name this metric CSD (Circular Spectrum Distance) due to its circular nature and its inherent relation to the Fourier Spectrum. We find that this metric, as opposed to Frechet Inception Distance or Inception Score, detects overfitting during training in terms of generator memorisation without making use of any pretrained network. The conclusions are generalized to CelebA-HQ as a benchmark dataset.en
dc.description.versionversión final
dc.identifier.urihttps://hdl.handle.net/20.500.14468/14128
dc.language.isoen
dc.publisherUniversidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
dc.relation.centerFacultades y escuelas::E.T.S. de Ingeniería Informática
dc.relation.degreeMáster Universitario en I.A. Avanzada: Fundamentos, Métodos y Aplicaciones
dc.relation.departmentInteligencia Artificial
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject.keywordsGAN metric
dc.subject.keywordsFourier Spectrum
dc.subject.keywordsoverfitting
dc.subject.keywordsmemorisation
dc.titleDetecting overfitting in GANs with a metric based on the Fourier spectrumes
dc.typetesis de maestríaes
dc.typemaster thesisen
dspace.entity.typePublication
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Gamazo_Tejero_Angel_Javier_TFM.pdf
Tamaño:
7.49 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Trabajos de fin de máster (TFM)