EUVIMEDEUVIMED entdecken
Crossref

Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks

José Ángel Díaz-Francés iD, José David Fernández-Rodríguez iD, Karl Thurnhofer-Hemsi iD, Ezequiel López-Rubio iD

International Journal of Neural Systems · 2024-11 · 34 (11)

DOI: 10.1142/s0129065724500576 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 15.08.2024. Verfasst von José Ángel Díaz-Francés und 3 weiteren Autor:innen. Beteiligte Einrichtung: ITIS Software, University of Málaga, Calle Arquitecto Francisco Peñalosa 18, Málaga 29010, Spain. Hauptthemen laut MEDLINE: Deep Learning, Neural Networks, Computer, Semantics, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: The Autonomous Government of Andalusia, The Ministry of Science and Innovation of Spain, the University of Málaga.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by [Formula: see text] and [Formula: see text]. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to [Formula: see text] for the binary image segmentation approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNeural Networks, ComputerSemanticsImage Processing, Computer-AssistedHumansSupervised Machine Learning

Stichwörter der Autor:innen

Semantic segmentationdiffusion modelsemi-supervised

Autor:innen und Institutionen

  • ITIS Software, University of Málaga, Calle Arquitecto Francisco Peñalosa 18, Málaga 29010, Spain.

ORCID-Profile: José Ángel Díaz-Francés, José David Fernández-Rodríguez, Karl Thurnhofer-Hemsi, Ezequiel López-Rubio

Förderung

  • The Autonomous Government of Andalusia
  • The Ministry of Science and Innovation of Spain
  • the University of Málaga
  • Detection of coronary stenosis using deep learning applied to coronary angiography
  • Intelligent Clinical Decision Support System for NonObstructive Coronary Artery Disease in Coronarographies
  • Detección de trayectorias anómalas de vehículos en cámaras de tráfico
  • Sistema de Videovigilancia basado en cámaras itinerantes robotizadas
  • NVIDIA Corporation with the donation of a RTX

Zitieren

APA

Díaz-Francés, J. Á., Fernández-Rodríguez, J. D., Thurnhofer-Hemsi, K., & López-Rubio, E. (2024). Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks. International Journal of Neural Systems, 34(11). https://doi.org/10.1142/s0129065724500576

Vancouver

Díaz-Francés JÁ, Fernández-Rodríguez JD, Thurnhofer-Hemsi K, López-Rubio E. Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks. International Journal of Neural Systems. 2024;34(11). doi:10.1142/s0129065724500576

BibTeX
@article{DazFrancs2024,
  author = {Díaz-Francés, José Ángel and Fernández-Rodríguez, José David and Thurnhofer-Hemsi, Karl and López-Rubio, Ezequiel},
  title = {Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks},
  journal = {International Journal of Neural Systems},
  year = {2024},
  volume = {34},
  number = {11},
  doi = {10.1142/s0129065724500576}
}
Kostenlos starten →