Class Balanced Sampling for the Training in GANs

  • Full Access Full Access
  • Onsite Student Access Onsite Student Access
  • Onsite Experience Onsite Experience
  • Virtual Full Access Virtual Full Access
  • Virtual Basic Access Virtual Basic Access

*All presentations are available in the virtual platform on-demand. The posters will also be exhibited onsite in Hall E, Tokyo International Forum from 15 – 17 December 2021.

Abstract: We propose class standardized critic score based sample selection which enables class balanced sample selection. Our method achieves improved FID score and Intra-FID score compared to prior Top-k selection.

Author(s)/Presenter(s):
Sanghun Kim, KHU, South Korea
Seungkyu Lee, KHU, South Korea

Back

SICAF
VRST