Research map / Probabilistic and scientific modeling / Variational and generative sampling
Gromov-Wasserstein Autoencoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GWAE (FNP) instead of DIP-VAE-I | Disentanglement on 3D Shapes · 3D Shapes | DCI-C: 0.8609 ± 0.0003 -> 0.9080 ± 0.0002 | Helped |
| Use GWAE (FNP) instead of WAE | Disentanglement on 3D Shapes · 3D Shapes | DCI-D: 0.7544 ± 0.0004 -> 0.7024 ± 0.0002 | Hurt |
| Use GWAE (FNP) instead of FactorVAE | Disentanglement on 3D Shapes · 3D Shapes | DCI-I: 0.9961 ± 0.0002 -> 0.9966 ± 0.0002 | Helped |
| Use GWAE (NP) instead of 2-Stage VAE | Generation on CelebA · CelebA test | FID: 34* -> 45.3 | Hurt |
| Use GWAE (NP) instead of β-VAE | Reconstruction on CelebA · CelebA test | PSNR [dB]: 22.71 -> 22.82 | Helped |
Closest papers by meaning
- Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency (NeurIPS 2021 · similarity 0.90)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.90)
- StrWAEs to Invariant Representations (ICML 2024 · similarity 0.89)
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models (NeurIPS 2017 · similarity 0.88)
- Trading Information between Latents in Hierarchical Variational Autoencoders (ICLR 2023 · similarity 0.88)
- Wasserstein Auto-Encoders (ICLR 2018 · similarity 0.88)
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.