AI Paper Atlas

Research map / Image generation / GANs

Dual Projection Generative Adversarial Networks for Conditional Image Generation

Ligong Han, Martin Renqiang Min, Anastasis Stathopoulos, Yu Tian, Ruijiang Gao, Asim Kadav, Dimitris N. Metaxas

ICCV 2021 · Image generation › GANs · approach: Stabilized GAN training · 22 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 dual projection (untied class embeddings with classification losses) to Proj-GAN (ablation)Proj-GAN · VGGFace200FID: 61.27 -> 23.15Improved
add dual projection to Proj-GAN (ablation)Proj-GAN · ImageNet 64x64 (60k iters)FID: 24.57 -> 21.46Improved
add dual projection to Proj-GAN (ablation)Proj-GAN · CIFAR100FID: 10.02 -> 10.55Hurt
add the two cross-entropy label-matching losses (lambda > 0 instead of lambda = 0) (ablation)P2GAN · VGGFace200FID: 62.46 -> 23.15Improved
keep the psi residual term (do not set psi to zero) (ablation)P2GAN · VGGFace200FID: 87.01 -> 23.15Improved
use dual projection instead of naive hybrid of Proj-GAN and f-cGAN losses (ablation)P2GAN · VGGFace200FID: 32.31 -> 23.15Improved
add amortized per-sample weights with penalty (P2GAN-ap) to P2GANP2GAN · VGGFace200FID: 23.15 -> 18.99Improved
add amortized per-sample weights with penalty (P2GAN-ap) to P2GANP2GAN · ImageNet 64x64 (80k iters)FID: 19.22 -> 18.31Improved
add amortized per-sample weights with penalty (P2GAN-ap) to P2GANP2GAN · CIFAR100 (62k iters)FID: 10.55 -> 9.82Improved
add a penalty term on lambda to scalar-weighted P2GAN (P2GAN-s to P2GAN-sp) (ablation)P2GAN-s · ImageNet 64x64 (80k iters)FID: 18.62 -> 20.68 (ImageNet), 9.03 -> 9.51 (CIFAR100), 20.59 -> 20.18 (VGGFace200)Mixed
use the alternative weighting (fix weight of L_D to 1) for scalar weighting (ablation)P2GAN-s · CIFAR100 and VGGFace200FID: 9.03 -> 9.49 (CIFAR100), 20.59 -> 20.21 (VGGFace200)No clear effect
add adaptive weights (P2GAN-w) to P2GANP2GAN · VGGFace200max-FID: 209.86 -> 127.43Improved

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