AI Paper Atlas

Research map / Image generation / Editing and style transfer

SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation

Xuning Shao, Weidong Zhang

ICCV 2021 · Image generation › Editing and style transfer · approach: Image-to-image translation · 37 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 channel-wise mean feature (ablation)SPatchGAN discriminator · Selfie-to-AnimeFID: 84.1 -> 83.3Improved
add channel-wise mean feature (ablation)SPatchGAN discriminator · Selfie-to-AnimeKID: 0.0228 -> 0.0214Improved
add channel-wise max feature (ablation)SPatchGAN discriminator · Selfie-to-AnimeFID: 83.8 -> 83.3Improved
add channel-wise standard deviation feature (ablation)SPatchGAN discriminator · Selfie-to-AnimeFID: 84.9 -> 83.3Improved
add channel-wise standard deviation feature (ablation)SPatchGAN discriminator · Selfie-to-AnimeKID: 0.0214 -> 0.0214No clear effect
use SPatchGAN discriminator instead of multi-scale PatchGAN (ablation)SPatchGAN · Selfie-to-AnimeFID: 94.0 -> 83.3Improved
use SPatchGAN discriminator instead of multi-scale PatchGAN (ablation)SPatchGAN · Selfie-to-AnimeKID: 0.0362 -> 0.0214Improved
add weak cycle constraint (ablation)SPatchGAN · Selfie-to-AnimeFID: 82.4 -> 83.3Hurt
add weak cycle constraint (ablation)SPatchGAN · Male-to-FemaleFID: 11.4 -> 8.73Improved
add weak cycle constraint (ablation)SPatchGAN · Glasses RemovalFID: 16.2 -> 13.9Improved
replace CycleGAN discriminator with SPatchGAN discriminator (ablation)CycleGAN · Male-to-FemaleFID: 24.5 -> 13.4Improved
replace CycleGAN discriminator with SPatchGAN discriminator (ablation)CycleGAN · Male-to-FemaleKID: 0.0240 -> 0.0107Improved

Later papers that compared with this method

1 later accepted paper reports SpatchGAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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