AI Paper Atlas

Research map / Image generation / GANs

Generalized Loss-Sensitive Adversarial Learning with Manifold Margins

Marzieh Edraki, Guo-Jun Qi

ECCV 2018 · Image generation › GANs · approach: Stabilized GAN training · 27 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
replace ambient-only margin with ambient plus manifold margin via pullback mapping (LSAL vs LS-GAN)LS-GAN · CIFAR-10 generationInception score: 5.83 -> 6.43Improved
LSAL versus ALI for image generationALI · CIFAR-10 generationInception score: 4.98 -> 6.43Improved
use LSAL instead of ALI for semi-supervised learning with 1000 labelsALI · CIFAR-10 semi-supervised (1000 labels)classification error (%): 19.98 -> 18.83Improved
LSAL versus ALI with 8000 labelsALI · CIFAR-10 semi-supervised (8000 labels)classification error (%): 17.05 -> 14.17Improved
LSAL versus CLS-GAN with 4000 labelsCLS-GAN · CIFAR-10 semi-supervised (4000 labels)classification error (%): 17.3 -> 16.22Improved
LSAL versus CLS-GAN on SVHN with 1000 labelsCLS-GAN · SVHN semi-supervised (1000 labels)classification error (%): 5.98 -> 5.46Improved
LSAL versus Improved GAN on SVHN with 1000 labelsImproved GAN · SVHN semi-supervised (1000 labels)classification error (%): 8.11 -> 5.46Improved
increase labeled examples from 1000 to 8000 (ablation)LSAL · CIFAR-10 semi-supervisedclassification error (%): 18.83 -> 14.17Improved

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