ComGAN: Toward GANs Exploiting Multiple Samples
This work addresses a specific bottleneck in GAN training for researchers, offering incremental improvements over existing relativistic GANs.
The paper tackles the problem of improving GAN performance by enabling the generator to use comparative samples, proposing ComGAN and equality regularization, which achieve the best FID scores in 7 out of 8 cases compared to ordinary and relativistic GANs.
In this paper, we propose ComGAN(ComparativeGAN) which allows the generator in GANs to refer to the semantics of comparative samples(e.g. real data) by comparison. ComGAN generalizes relativistic GANs by using arbitrary architecture and mostly outperforms relativistic GANs in simple input-concatenation architecture. To train the discriminator in ComGAN, we also propose equality regularization, which fits the discriminator to a neutral label for equally real or fake samples. Equality regularization highly boosts the performance of ComGAN including WGAN while being exceptionally simple compared to existing regularizations. Finally, we generalize comparative samples fixed to real data in relativistic GANs toward fake data and show that such objectives are sound in both theory and practice. Our experiments demonstrate superior performances of ComGAN and equality regularization, achieving the best FIDs in 7 out of 8 cases of different losses and data against ordinary GANs and relativistic GANs.