Non Gaussian Denoising Diffusion Models

06/14/2021
by   Eliya Nachmani, et al.
0

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom, could help the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we show that noise from Gamma distribution provides improved results for image and speech generation. Moreover, we show that using a mixture of Gaussian noise variables in the diffusion process improves the performance over a diffusion process that is based on a single distribution. Our approach preserves the ability to efficiently sample state in the training diffusion process while using Gamma noise and a mixture of noise.

READ FULL TEXT
research
10/10/2021

Denoising Diffusion Gamma Models

Generative diffusion processes are an emerging and effective tool for im...
research
04/12/2023

Diffusion models with location-scale noise

Diffusion Models (DMs) are powerful generative models that add Gaussian ...
research
10/11/2022

Markup-to-Image Diffusion Models with Scheduled Sampling

Building on recent advances in image generation, we present a fully data...
research
07/26/2023

How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?

Transformer-based pretrained language models (PLMs) have achieved great ...
research
02/18/2023

Modelos Generativos basados en Mecanismos de Difusión

Diffusion-based generative models are a design framework that allows gen...
research
02/14/2023

Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions

Diffusion-based generative models (DBGMs) perturb data to a target noise...
research
05/15/2023

Common Diffusion Noise Schedules and Sample Steps are Flawed

We discover that common diffusion noise schedules do not enforce the las...

Please sign up or login with your details

Forgot password? Click here to reset