Score-Guided Generative Adversarial Networks

Minhyeok Lee, Junhee Seok

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

We propose a generative adversarial network (GAN) that introduces an evaluator module using pretrained networks. The proposed model, called a score-guided GAN (ScoreGAN), is trained using an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of the generator. Using another pretrained network instead of the Inception network, ScoreGAN circumvents overfitting of the Inception network such that the generated samples do not correspond to adversarial examples of the Inception network. In addition, evaluation metrics are employed only in an auxiliary role to prevent overfitting. When evaluated using the CIFAR-10 dataset, ScoreGAN achieved an Inception score of 10.36 ± 0.15, which corresponds to state-of-the-art performance. To generalize the effectiveness of ScoreGAN, the model was evaluated further using another dataset, CIFAR-100. ScoreGAN outperformed other existing methods, achieving a Fréchet Inception distance (FID) of 13.98.

Original languageEnglish
Article number701
JournalAxioms
Volume11
Issue number12
DOIs
Publication statusPublished - 2022 Dec

Bibliographical note

Publisher Copyright:
© 2022 by the authors.

Keywords

  • GAN
  • Inception score
  • generative adversarial network
  • generative model
  • image generation
  • image synthesis
  • scoreGAN

ASJC Scopus subject areas

  • Analysis
  • Algebra and Number Theory
  • Mathematical Physics
  • Logic
  • Geometry and Topology

Fingerprint

Dive into the research topics of 'Score-Guided Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this