AI Paper Atlas

Research map / Image generation / GANs

Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

Runfa Chen, Wenbing Huang, Binghui Huang, Fuchun Sun, Bin Fang

CVPR 2020 · Image generation › GANs · approach: GAN-based image manipulation · 247 citations (OpenAlex)

Check 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
reuse discriminator features as the target-domain encoder (ablation)NICE-GAN · cat ↔ dogFID: 80.75 -> 63.80; 64.36 -> 51.49Improved
add residual attention to discriminator features (ablation)NICE-GAN · dog ↔ catFID: 80.75 -> 67.60Improved
add residual attention to discriminator features (ablation)NICE-GAN · cat → dogFID: 51.49 -> 44.67Hurt
decrease shared encoder-discriminator layers by 1 (ablation)NICE-GAN · dog → catFID: 48.79 -> 48.55Improved
increase shared encoder-discriminator layers by 1 (ablation)NICE-GAN · dog → catFID: 48.79 -> 53.52Hurt
decrease shared encoder-discriminator layers by 1 (ablation)NICE-GAN · cat → dogFID: 44.67 -> 52.92Hurt
increase shared encoder-discriminator layers by 1 (ablation)NICE-GAN · cat → dogFID: 44.67 -> 54.90Hurt
remove global-scale classifier C² (ablation)NICE-GAN · dog → catFID: 48.79 -> 203.56Hurt
remove global-scale classifier C² (ablation)NICE-GAN · cat → dogFID: 44.67 -> 238.62Hurt
remove middle- and global-scale classifiers C¹ and C² (ablation)NICE-GAN · dog → catFID: 48.79 -> 216.03Hurt
remove middle- and global-scale classifiers C¹ and C² (ablation)NICE-GAN · cat → dogFID: 44.67 -> 231.24Hurt
use NICE-GAN instead of the strongest reported FID baselineunsupervised image translation · zebra → horseFID: 145.47 -> 149.48Hurt

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