AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions

Zhilin Zheng, Li Sun

CVPR 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Hierarchical VAEs and posterior collapse · 58 citations (OpenAlex)

Check 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
Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priorsVAE image generation · FaceScrubInception Score: 16.75 -> 17.91Improved
Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priorsVAE image generation · CIFAR-10Inception Score: 6.99 -> 7.04Improved
Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priorsVAE image generation · CUB-200-2011Inception Score: 91.14 -> 100.86Improved
Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priorsVAE image generation · CIFAR-100Inception Score: 6.68 -> 6.70Improved
Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each classVAE image generation · FaceScrubintra-class diversity: 0.0141 -> 0.0157Improved
Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each classVAE image generation · CIFAR-10intra-class diversity: 0.0136 -> 0.0149Improved
Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each classVAE image generation · CUB-200-2011intra-class diversity: 0.0195 -> 0.0192Hurt
Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each classVAE image generation · CIFAR-100intra-class diversity: 0.0179 -> 0.0190Improved

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