AI Paper Atlas

Research map / Image generation / GANs

Generator Knows What Discriminator Should Learn in Unconditional GANs

Gayoung Lee, Hyunsu Kim, Junho Kim, Seonghyeon Kim, Jung-Woo Ha, Yunjey Choi

ECCV 2022 · Image generation › GANs · approach: Conditional GANs · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GGDR (generator-feature-map supervision of discriminator)StyleGAN2 · FFHQ fullFID: 3.66 -> 3.14Improved
add GGDRStyleGAN2 · FFHQ 2kFID: 78.80 -> 70.59Improved
add GGDRADA · FFHQ 2kFID: 16.49 -> 18.28Hurt
add GGDRADA · FFHQ 10kFID: 8.29 -> 6.11Improved
add GGDRADA · CIFAR-10FID: 2.92 -> 2.15Improved
add GGDRADA · CIFAR-10IS: 9.83 -> 10.02Improved
add GGDRStyleGAN2 · LSUN CatFID: 7.98 -> 5.28Improved
add GGDRStyleGAN2 · LSUN CatRecall: 0.27 -> 0.38Improved
add GGDRStyleGAN2 · FFHQPrecision: 0.69 -> 0.69No clear effect
add GGDRADA · AFHQ DogFID: 7.40 -> 4.59Improved
add GGDRADA · LandscapePrecision: 0.72 -> 0.69Hurt
increase guidance feature map size from none to 64x64 (ablation)StyleGAN2+GGDR · LSUN CatFID: 7.98 -> 5.28Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy