Research map / Image generation / GANs
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
Sam Bond-Taylor, Adam Leach, Yang Long, Chris G. Willcocks
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use StyleGAN2 + ADA instead of DCGAN | GAN · CIFAR-10 | FID: 37.11 -> 2.42 | Improved |
| use DDPM++ Continuous instead of Denoising Diffusion | diffusion model · CIFAR-10 | FID: 3.17 -> 2.20 | Improved |
| use Sparse Transformer + DistAug instead of Gated PixelCNN | autoregressive model · CIFAR-10 | FID: 65.93 -> 14.74 | Improved |
| use Sparse Transformer + DistAug instead of PixelRNN | autoregressive model · CIFAR-10 | NLL (bits per dim): 3.00 -> 2.66 | Improved |
| use VD-VAE instead of Convolutional VAE | VAE · CIFAR-10 | NLL (bits per dim): 4.54 -> 2.87 | Improved |
| use Residual Flow instead of RealNVP | normalizing flow · CIFAR-10 | NLL (bits per dim): 3.49 -> 3.28 | Improved |
| add VAEBM hybrid VAE-EBM instead of IGEBM | energy-based model · CIFAR-10 | FID: 37.9 -> 12.19 | Improved |
Closest papers by meaning
- On Unifying Deep Generative Models (ICLR 2018 · similarity 0.90)
- A Large-Scale Study on Regularization and Normalization in GANs (ICML 2019 · similarity 0.89)
- An Architecture for Deep, Hierarchical Generative Models (NeurIPS 2016 · similarity 0.88)
- Adaptive Density Estimation for Generative Models (NeurIPS 2019 · similarity 0.88)
- Towards Principled Methods for Training Generative Adversarial Networks (ICLR 2017 · similarity 0.88)
- Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding (ICML 2024 · similarity 0.87)
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.
