본문 바로가기
  • Home

Enhanced ACGAN based on Progressive Step Training and Weight Transfer

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(3), pp.11-20
  • DOI : 10.9708/jksci.2024.29.03.011
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : January 11, 2024
  • Accepted : March 15, 2024
  • Published : March 29, 2024

Jinmo Byeon 1 Inshil Doh 2 Dana Yang 1

1한국성서대학교
2이화여자대학교

Accredited

ABSTRACT

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.