AI Paper Atlas

Research map / Image generation / GANs

Semi-supervised FusedGAN for Conditional Image Generation

Navaneeth Bodla, Gang Hua, Rama Chellappa

ECCV 2018 · Image generation › GANs · approach: Conditional GANs · 62 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 semi-supervised training with unpaired images (ablation)FusedGAN · CUB birds (CUB images only, no extra NABirds)inception score: 2.69 -> 3.00Improved
use FusedGAN instead of StackGAN stage-I64x64 text-to-image · CUB birds text-to-imageinception score: 2.95 -> 3.00Improved
use FusedGAN instead of GAN-INT-CLS64x64 text-to-image · CUB birds text-to-imageinception score: 2.88 -> 3.00Improved
stack high-resolution generator on FusedGANFusedGAN · CUB birds text-to-image (high resolution)inception score: 3.00 -> 3.92Improved
use FusedGAN instead of StackGAN stage-IIhigh-res text-to-image · CUB birds text-to-image (high resolution)inception score: 3.70 -> 3.92Improved
use FusedGAN instead of attr2image (no segmentation supervision)attribute-to-face · CelebA attribute-to-faceinception score: 1.87 -> 2.63Improved

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