AI Paper Atlas

Research map / Image generation / GANs

Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms

Xin Ding, Yongwei Wang, Zuheng Xu, William J. Welch, Z. Jane Wang

TPAMI 2022 · Image generation › GANs · approach: Stabilized GAN training · 70 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
use improved label input (ILI) instead of naive label input (NLI) (ablation)CcGAN (SVDL) · Cell-200 (64x64)Intra-FID: 56.078 -> 7.266Improved
use ILI instead of NLI (ablation)CcGAN (SVDL) · RC-49 (64x64)Intra-FID: 0.515 -> 0.389Improved
use ILI instead of NLI (ablation)CcGAN (SVDL) · UTKFace (64x64)Intra-FID: 0.547 -> 0.425Improved
use ILI instead of NLI (ablation)CcGAN (SVDL) · Steering Angle (64x64)Intra-FID: 1.866 -> 1.546Improved
use soft vicinal loss (SVDL) instead of hard vicinal loss (HVDL) (ablation)CcGAN (ILI) · RC-49 (64x64)Intra-FID: 0.424 -> 0.389Improved
use SVDL instead of HVDL (ablation)CcGAN (ILI) · Cell-200 (64x64)Intra-FID: 8.759 -> 7.266Improved
use SVDL instead of HVDL (ablation)CcGAN (NLI) · Cell-200 (64x64)Intra-FID: 50.052 -> 56.078Hurt
replace class binning (cGAN) with CcGAN vicinal losses and ILIcGAN (150 classes) · RC-49 (64x64)Intra-FID: 1.720 -> 0.389Improved
use CcGAN (SVDL+ILI) instead of cGAN (concat)cGAN (concat) · RC-49 (64x64)Label Score: 30.212 -> 1.940Improved
use SFID with nearby real images instead of Intra-FID on seen anglesevaluation metric · RC-49 HVDL+ILIFID score: 1.032 -> 0.401Improved
add DiffAugment and BigGAN to CcGAN (SVDL+ILI) versus SNGANCcGAN (SVDL+ILI) · RC-49Intra-FID: 0.389 -> 0.086Improved
use CcGAN (SVDL+ILI) with SNGAN instead of ReACGAN with advanced trainingReACGAN · RC-49Intra-FID: 0.178 -> 0.389Hurt

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