Unrealistic feature suppression (UFS) module keeps high-quality features and suppresses unrealistic features . UFS module keeps the training stability of networks and improves the quality ofgenerated images . We demonstrate effectiveness of the module on various models such as WGAN-GP, SNGAN, and BigGAN . We achieved better Frechet inception distance and inception score compared to various baseline models . We also visualize how effectively our module suppressesunrealistic features through class activation maps. We demonstrate the effectiveness of UFS modules on variousmodels such as . WGAN .GP, . SngAN, . BigGAN, BigGAN and WGAN

Author(s) : Sanghun Kim, SeungKyu Lee

Links : PDF - Abstract

Code :
Coursera

Keywords : module - biggan - wgan - ufs - unrealistic -

Leave a Reply

Your email address will not be published. Required fields are marked *