TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Generation	CelebA 256x256	ANF Huang et al. (2020)	bpd	0.72	# 6
Image Generation	CIFAR-10	ANF Huang et al. (2020)	bits/dimension	3.05	# 36
Image Generation	ImageNet 32x32	ANF Huang et al. (2020)	bpd	3.92	# 16

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-normalizing-flows-bridging-the-gap/image-generation-on-celeba-256x256)](https://paperswithcode.com/sota/image-generation-on-celeba-256x256?p=augmented-normalizing-flows-bridging-the-gap)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-normalizing-flows-bridging-the-gap/image-generation-on-imagenet-32x32)](https://paperswithcode.com/sota/image-generation-on-imagenet-32x32?p=augmented-normalizing-flows-bridging-the-gap)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/augmented-normalizing-flows-bridging-the-gap/image-generation-on-cifar-10)](https://paperswithcode.com/sota/image-generation-on-cifar-10?p=augmented-normalizing-flows-bridging-the-gap)`

Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models

17 Feb 2020 · Chin-wei Huang, Laurent Dinh, Aaron Courville ·

In this work, we propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of sampling and evaluation of a lower bound on the likelihood. Theoretically, we prove the proposed flow can approximate a Hamiltonian ODE as a universal transport map. Empirically, we demonstrate state-of-the-art performance on standard benchmarks of flow-based generative modeling.

PDF Abstract

Code

Add Remove Mark official

mj-will/augmented-flows

Tasks

Add Remove

Image Generation

Datasets

CIFAR-10

MNIST

CelebA

Results from the Paper

Edit

Ranked #6 on Image Generation on CelebA 256x256

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Image Generation	CelebA 256x256	ANF Huang et al. (2020)	bpd	0.72	# 6	Compare
Image Generation	CIFAR-10	ANF Huang et al. (2020)	bits/dimension	3.05	# 36	Compare
Image Generation	ImageNet 32x32	ANF Huang et al. (2020)	bpd	3.92	# 16	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove