Evaluating a Synthetic Image Dataset Generated with Stable Diffusion

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

1 Citation (Scopus)

Abstract

We generate synthetic images with the ``Stable Diffusion'' image generation model using the Wordnet taxonomy and the definitions of concepts it contains. This synthetic image database can be used as training data for data augmentation in machine learning applications, and it is used to investigate the capabilities of the Stable Diffusion model. Analyzes show that Stable Diffusion can produce correct images for a large number of concepts but also a large variety of different representations. The results show differences depending on the test concepts considered and problems with very specific concepts. These evaluations were performed using a vision transformer model for image classification.
Original languageEnglish
Title of host publicationProceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
EditorsXin-She Yang, R. Simon Sherratt, Nilanjan Dey, Amit Joshi
Place of PublicationSingapore
PublisherSpringer
Pages805-818
Number of pages14
ISBN (Print)9789819932429
DOIs
Publication statusPublished - 2023

Publication series

NameLecture Notes in Networks and Systems
Volume693 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Keywords

  • Image classification
  • Image dataset
  • Image generation
  • Wordnet

Cite this