Density Estimation On Cifar 10
평가 지표
NLL (bits/dim)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | NLL (bits/dim) | Paper Title | Repository |
|---|---|---|---|
| DDPM | 3.69 | Denoising Diffusion Probabilistic Models | |
| MAF | - | Masked Autoregressive Flow for Density Estimation | |
| FFJORD | 3.4 | FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models | |
| Flow matching | 2.99 | Flow Matching for Generative Modeling | |
| RNODE | 3.38 | How to train your neural ODE: the world of Jacobian and kinetic regularization | |
| Pixel CNN | 3.03 | Conditional Image Generation with PixelCNN Decoders | |
| VDM | 2.65 | Variational Diffusion Models | |
| Pixel CNN ++ | 2.92 | PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications | |
| MULAN | 2.55 | Diffusion Models With Learned Adaptive Noise | |
| MRCNF | 3.54 | Multi-Resolution Continuous Normalizing Flows | |
| i-DODE | 2.42 | Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs | |
| Image Transformer | 2.90 | Image Transformer | - |
| score SDE | 2.99 | Score-Based Generative Modeling through Stochastic Differential Equations | |
| BSI | 2.64 | Generative Modeling with Bayesian Sample Inference |
0 of 14 row(s) selected.