Image Generation On Mnist
Metrics
FID
Results
Performance results of various models on this benchmark
Model Name | FID | Paper Title | Repository |
|---|---|---|---|
| JKO-iFlow | 7.95 | - | - |
| Spiking-Diffusion | 27.61 | Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks | - |
| Locally Masked PixelCNN (8 orders) | - | Locally Masked Convolution for Autoregressive Models | - |
| GLF+perceptual loss (ours) | 5.8 | Generative Latent Flow | - |
| Transition Matrix | - | Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices | |
| HypGAN | 7.87 | Hyperbolic Generative Adversarial Network | - |
| PresGAN | 38.53 | Prescribed Generative Adversarial Networks | - |
| Feature Alignment | 37.50 | Feature Alignment as a Generative Process | - |
| Sliced Iterative Generator | 4.5 | Sliced Iterative Normalizing Flows | - |
| PR-GLOW- Precision | 12.884 | - | - |
| RNODE | - | How to train your neural ODE: the world of Jacobian and kinetic regularization | - |
| Residual Flow | - | Residual Flows for Invertible Generative Modeling | - |
| MintNet | - | MintNet: Building Invertible Neural Networks with Masked Convolutions | - |
| PR-GLOW- Recall | 4.45 | - | - |
| i-ResNet | - | Invertible Residual Networks | - |
0 of 15 row(s) selected.