Research map / Probabilistic and scientific modeling / Variational and generative sampling
On Unifying Deep Generative Models
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 |
|---|---|---|---|
| Add importance weighting to GAN training | GAN · MNIST | Inception score: 8.34±.03 -> 8.45±.04 | Helped |
| Add importance weighting to GAN training | GAN · SVHN | Inception score: 5.18±.03 -> 5.34±.03 | Helped |
| Add importance weighting to GAN training | GAN · CIFAR10 | Inception score: 7.86±.05 -> 7.89± .04 | Helped |
| Add importance weighting to conditional GAN training | CGAN · MNIST | Conditional generation accuracy: 0.985±.002 -> 0.987±.002 | Helped |
| Add importance weighting to conditional GAN training | CGAN · SVHN | Conditional generation accuracy: 0.797±.005 -> 0.798±.006 | Helped |
| Activate the discriminator to incorporate weighted generated samples | SVAE · MNIST test, 1% labeled data | Classification accuracy: 0.9412 -> 0.9425 | Helped |
| Activate the discriminator to incorporate weighted generated samples | SVAE · MNIST test, 10% labeled data | Classification accuracy: 0.9768 -> 0.9797 | Helped |
| Activate the discriminator | VAE · MNIST test, 1% training data | Variational lower bound: -122.89 -> -122.15 | Helped |
| Activate the discriminator | VAE · MNIST test, 10% training data | Variational lower bound: -104.49 -> -103.05 | Helped |
| Activate the discriminator | VAE · MNIST test, 100% training data | Variational lower bound: -92.53 -> -92.42 | Helped |
| Activate the discriminator | CVAE · MNIST test, 1% training data | Variational lower bound: -125.44 -> -122.88 | Helped |
| Activate the discriminator | CVAE · MNIST test, 10% training data | Variational lower bound: -102.63 -> -101.63 | Helped |
Closest papers by meaning
- Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs (ICML 2019 · similarity 0.92)
- Diagnosing and Enhancing VAE Models (ICLR 2019 · similarity 0.91)
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (ICML 2017 · similarity 0.91)
- A Primal-Dual link between GANs and Autoencoders (NeurIPS 2019 · similarity 0.91)
- Adaptive Density Estimation for Generative Models (NeurIPS 2019 · similarity 0.89)
- Generating Diverse High-Fidelity Images with VQ-VAE-2 (NeurIPS 2019 · similarity 0.89)
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.