AI Paper Atlas

Research map / Image generation / GANs

Sub-GAN: An Unsupervised Generative Model via Subspaces

Jie Liang, Jufeng Yang, Hsin-Ying Lee, Kai Wang, Ming-Hsuan Yang

ECCV 2018 · Image generation › GANs · approach: Stabilized GAN training · 24 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 refinement of cluster assignment in the discriminator (ablation)Sub-GAN · MNIST clustering (K=10), last epochclustering accuracy (%): 83.87 -> 85.32Improved
add refinement of cluster assignment in the discriminator (ablation)Sub-GAN · MNIST clustering (K=10), 1st epochclustering accuracy (%): 75.23 -> 77.12Improved
add refinement of cluster assignment in the discriminator (ablation)Sub-GAN · MNIST clustering (K=10), 40th epochclustering accuracy (%): 83.11 -> 84.24Improved
joint training of generator, discriminator and clusterer after SMR initializationSub-GAN · MNIST clustering (K=10)clustering accuracy (%): 73.39 -> 85.32Improved
joint training of generator, discriminator and clusterer after SMR initializationSub-GAN · CIFAR clustering (K=10)clustering accuracy (%): 56.24 -> 78.95Improved
use subspace-conditioned generation (Sub-GAN) instead of InfoGANInfoGAN · MNIST (K=10)diversity score: 2.11 -> 2.36Improved
use subspace-conditioned generation (Sub-GAN) instead of InfoGANInfoGAN · CIFAR (K=10)diversity score: 2.48 -> 2.72Improved
use Sub-GAN instead of IGANIGAN · CIFAR (K=10)diversity score: 2.20 -> 2.72Improved
increase number of clusters K from 10 to 20 (ablation)Sub-GAN · MNIST clusteringadjusted clustering accuracy (%): 85.32 -> 90.81Improved
increase number of clusters K from 10 to 20 (ablation)Sub-GAN · CIFAR clusteringadjusted clustering accuracy (%): 78.95 -> 82.44Improved
increase number of clusters K from 10 to 20 (ablation)DEC · MNIST clusteringadjusted clustering accuracy (%): 84.30 -> 83.02Hurt

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