Generating High Fidelity Data from Low-density Regions using Diffusion Models

April 05, 2022


Our work focuses on addressing sample deficiency from low-density regions of data manifold in common image datasets. We leverage diffusion process based generative models to synthesize novel images from low-density regions. We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold. Therefore, we modify the sampling process to guide it towards low-density regions while simultaneously maintaining the fidelity of synthetic data. We rigorously demonstrate that our process successfully generates novel high fidelity samples from low-density regions. We further examine generated samples and show that the model does not memorize low-density data and indeed learns to generate novel samples from low-density regions.

Download the Paper


Written by

Caner Hazirbas

Albert Gordo

Cristian Canton Ferrer

Firat Ozgenel

Vikash Sehwag



Research Topics

Computer Vision

Core Machine Learning

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.