atlas

Research map / Image generation / GANs

Twin Auxilary Classifiers GAN

NeurIPS 2019 · Image generation › GANs · approach: Stabilized GAN training · 31 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 twin auxiliary classifier C^mi (TAC-GAN) to AC-GANAC-GAN · CIFAR100FID: 82.45 -> 7.22Helped
add twin auxiliary classifier to AC-GANAC-GAN · ImageNet1000FID: 184.41 -> 23.75Helped
add twin auxiliary classifier to AC-GANAC-GAN · VGGFace200FID: 95.70 -> 29.12Helped
TAC-GAN instead of Projection cGANTAC-GAN · ImageNet1000IS: 38.05 -> 28.86Hurt
TAC-GAN instead of Projection cGANTAC-GAN · VGGFace2000FID: 22.42 -> 13.79Helped
add pacGAN packing to TAC-GAN (ablation)TAC-GAN · CIFAR100FID: 7.22 -> 6.79Helped
add pacGAN packing to AC-GAN (ablation)AC-GAN · CIFAR100FID: 82.45 -> 20.94Helped
increase classifier weight lambda_c (ablation)AC-GAN · Overlapping MNISTproportion of overlapping digit 0Hurt
vary lambda_c (ablation)TAC-GAN · CIFAR100IS/FIDNo clear effect

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