Research map / Probabilistic and scientific modeling / Variational and generative sampling
Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
Zhilin Zheng, Li Sun
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priors | VAE image generation · FaceScrub | Inception Score: 16.75 -> 17.91 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priors | VAE image generation · CIFAR-10 | Inception Score: 6.99 -> 7.04 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priors | VAE image generation · CUB-200-2011 | Inception Score: 91.14 -> 100.86 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches with class-specific Gaussian-mixture priors | VAE image generation · CIFAR-100 | Inception Score: 6.68 -> 6.70 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each class | VAE image generation · FaceScrub | intra-class diversity: 0.0141 -> 0.0157 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each class | VAE image generation · CIFAR-10 | intra-class diversity: 0.0136 -> 0.0149 | Improved |
| Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each class | VAE image generation · CUB-200-2011 | intra-class diversity: 0.0195 -> 0.0192 | Hurt |
| Disentangle the latent code into label-relevant and label-irrelevant branches to encourage varied samples within each class | VAE image generation · CIFAR-100 | intra-class diversity: 0.0179 -> 0.0190 | Improved |
Closest papers by meaning
- Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders (NeurIPS 2021 · similarity 0.87)
- Learning Latent Subspaces in Variational Autoencoders (NeurIPS 2018 · similarity 0.87)
- Disentangling Disentanglement in Variational Autoencoders (ICML 2019 · similarity 0.87)
- Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations (ICML 2023 · similarity 0.87)
- EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling (ICML 2025 · similarity 0.87)
- Information-theoretic Generalization Analysis for VQ-VAEs: A Role of Latent Variables (NeurIPS 2025 · similarity 0.86)
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.
