Simplified fréchet distance for generative adversarial nets

Chung Il Kim, Meejoung Kim, Seungwon Jung, Eenjun Hwang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We introduce a distance metric between two distributions and propose a Generative Adversarial Network (GAN) model: the Simplified Fréchet distance (SFD) and the Simplified Fréchet GAN (SFGAN). Although the data generated through GANs are similar to real data, GAN often undergoes unstable training due to its adversarial structure. A possible solution to this problem is considering Fréchet distance (FD). However, FD is unfeasible to realize due to its covariance term. SFD overcomes the complexity so that it enables us to realize in networks. The structure of SFGAN is based on the Boundary Equilibrium GAN (BEGAN) while using SFD in loss functions. Experiments are conducted with several datasets, including CelebA and CIFAR-10. The losses and generated samples of SFGAN and BEGAN are compared with several distance metrics. The evidence of mode collapse and/or mode drop does not occur until 3000k steps for SFGAN, while it occurs between 457k and 968k steps for BEGAN. Experimental results show that SFD makes GANs more stable than other distance metrics used in GANs, and SFD compensates for the weakness of models based on BEGAN-based network structure. Based on the experimental results, we can conclude that SFD is more suitable for GAN than other metrics.

Original languageEnglish
Article number1548
JournalSensors (Switzerland)
Volume20
Issue number6
DOIs
Publication statusPublished - 2020 Mar 2

Keywords

  • Generative adversarial net
  • Generative models
  • Image processing

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Simplified fréchet distance for generative adversarial nets'. Together they form a unique fingerprint.

  • Cite this