AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Triple Generative Adversarial Networks

Chongxuan Li, Kun Xu, Jun Zhu, Jiashuo Liu, Bo Zhang

TPAMI 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 64 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 the pseudo discriminative loss (alpha_P=3.0 vs 0.0) (ablation)Triple-GAN-V2 (mean teacher) · CIFAR10 (4000 labels), with augmentationerror rate (%): 13.68 -> 10.01Improved
add the pseudo discriminative loss (alpha_P=3.0 vs 0.0) (ablation)Triple-GAN-V2 (mean teacher) · CIFAR10 (4000 labels), no augmentationerror rate (%): 15.90 -> 12.41Improved
use alpha_P=3.0 instead of 10.0 (ablation)Triple-GAN-V2 · CIFAR10 (4000 labels), with augmentationerror rate (%): 11.97 -> 10.01Improved
use alpha_P=1.0 instead of 10.0 (ablation)Triple-GAN-V2 · CIFAR10 (4000 labels), no augmentationerror rate (%): 13.78 -> 13.10Improved
add Triple-GAN (G and D) to mean teacher classifier (ablation)Mean teacher · CIFAR10 (4000 labels), with augmentationerror rate (%): 13.18 -> 10.01Improved
add Triple-GAN to entropy regularized classifier (ablation)ER classifier · CIFAR10 (4000 labels), no augmentationerror rate (%): 21.98 -> 15.44Improved
add Triple-GAN to classifier without unlabeled loss (ablation)Plain classifier · CIFAR10 (4000 labels), no augmentationerror rate (%): 24.21 -> 17.88Improved
add standard data augmentation (ablation)Triple-GAN-V2 · CIFAR10 (4000 labels)error rate (%): 12.41 -> 10.01Improved
replace Improved-GAN with Triple-GAN-V1 (same classifier)Improved-GAN · SVHN (1000 labels)error rate (%): 8.11 -> 5.77Improved
add pseudo discriminative loss to Triple-GAN-V1 (ablation)Triple-GAN-V1 · SVHNerror rate (%): about 7.8% -> 2% betterImproved
add G and D to classifier on SVHN (ablation)Single semi-supervised classifier · SVHNerror rate (%): more than 10% error rate -> 5.77Improved
replace mean teacher with Triple-GAN-V2 under 26-layer ResNetMT · CIFAR10 (1000 labels), ResNeterror rate (%): 9.64 -> 8.41Improved

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