Density Estimation
358 papers with code • 15 benchmarks • 15 datasets
The goal of Density Estimation is to give an accurate description of the underlying probabilistic density distribution of an observable data set with unknown density.
Source: Contrastive Predictive Coding Based Feature for Automatic Speaker Verification
Benchmarks
These leaderboards are used to track progress in Density Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Density Estimation models and implementationsDatasets
CIFAR-10
ImageNet
MNIST
CelebA-HQ
BSD
Caltech-101
Omniglot
JHU-CROWD++
UCF-CC-50
Most implemented papers
Density estimation using Real NVP
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.
Importance Weighted Autoencoders
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference.
Masked Autoregressive Flow for Density Estimation
By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow.
MADE: Masked Autoencoder for Distribution Estimation
mgermain/MADE
•
•
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples.
Point-Set Registration: Coherent Point Drift
The goal of point set registration is to assign correspondences between two sets of points and to recover the transformation that maps one point set to the other.
PointConv: Deep Convolutional Networks on 3D Point Clouds
DylanWusee/pointconv
•
•
CVPR 2019
Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
Neural Spline Flows
bayesiains/nsf
•
•
NeurIPS 2019
A normalizing flow models a complex probability density as an invertible transformation of a simple base density.
Progressive Distillation for Fast Sampling of Diffusion Models
google-research/google-research
•
•
ICLR 2022
Second, we present a method to distill a trained deterministic diffusion sampler, using many steps, into a new diffusion model that takes half as many sampling steps.
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
PixelSNAIL: An Improved Autoregressive Generative Model
neocxi/pixelsnail-public
•
•
ICML 2018
Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio.
