Generator Knows What Discriminator Should Learn in Unconditional GANs
Abstract
Recent methods for conditional image generation benefit from dense supervision such as segmentation label maps to achieve high-fidelity. However, it is rarely explored to employ dense supervision for unconditional image generation. Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps. From our empirical evidences, we propose a new generator-guided discriminator regularization(GGDR) in which the generator feature maps supervise the discriminator to have rich semantic representations in unconditional generation. In specific, we employ an U-Net architecture for discriminator, which is trained to predict the generator feature maps given fake images as inputs. Extensive experiments on mulitple datasets show that our GGDR consistently improves the performance of baseline methods in terms of quantitative and qualitative aspects. Code is available at https://github.com/naver-ai/GGDR
Cite
@article{arxiv.2207.13320,
title = {Generator Knows What Discriminator Should Learn in Unconditional GANs},
author = {Gayoung Lee and Hyunsu Kim and Junho Kim and Seonghyeon Kim and Jung-Woo Ha and Yunjey Choi},
journal= {arXiv preprint arXiv:2207.13320},
year = {2022}
}
Comments
Accepted to ECCV 2022. Our code is available at https://github.com/naver-ai/GGDR