Yunjey Choi, Jung-Woo Ha, Hyunsu Kim, Junho Kim, Gayoung Lee, Seonghyeon Kim
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent methods for conditional image generation benefit from dense supervision such as segmentation label maps to achieve highfidelity. 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2207.13320")
get_code_for_paper("2207.13320")
have("2207.13320")
Connect an agent — have() is free.