AI Paper Atlas

Research map / Image generation / GANs

Generative Adversarial Minority Oversampling

Sankha Subhra Mullick, Shounak Datta, Swagatam Das

ICCV 2019 · Image generation › GANs · approach: Stabilized GAN training · 251 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 a discriminator D to the convex generator (GAMO vs GAMO\D) (ablation)GAMO · MNIST (IR 100, LS loss)ACSA: 0.88 -> 0.91Improved
add a discriminator D to the convex generator (GAMO vs GAMO\D) (ablation)GAMO · Fashion-MNIST (IR 100, LS loss)ACSA: 0.82 -> 0.83No clear effect
add a discriminator D to the convex generator (GAMO vs GAMO\D) (ablation)GAMO · CIFAR10 (IR 56.25)GM: 0.40 -> 0.43Improved
use convex generator instead of conditional generator cG (both with D) (ablation)GAMO · MNIST (IR 100, LS loss)ACSA: 0.85 -> 0.91Improved
add discriminator D to conditional generator cG (ablation)cG+CN · MNIST (IR 100, LS loss)GM: 0.85 -> 0.82Hurt
train generator adversarially against classifier (cG+CN) instead of cGAN+CN (ablation)cGAN+CN · MNIST (IR 100, LS loss)ACSA: 0.89 -> 0.86Hurt
use least-square loss instead of cross entropy (ablation)GAMO · MNISTACSA: 0.89 -> 0.91Improved
use least-square loss instead of cross entropy (ablation)GAMO · Fashion-MNISTACSA: 0.82 -> 0.83Improved
use GAMO instead of baseline classifierCN · SUN397 (50 classes)ACSA: 0.26 -> 0.32Improved
use GAMO instead of data augmentationAugment+CN · SVHN (IR 56.25)ACSA: 0.69 -> 0.76Improved
use GAMO2pix instead of cDCGANimage generation · Fashion-MNISTFID: 5.57 -> 0.75Improved
use GAMO instead of baseline classifier at larger data sizeCN · CelebA-Large (test)ACSA: 0.71 -> 0.75Improved

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