The reviewed record of science sign in
Pith

arxiv: 2203.17260 · v2 · pith:EFA5WFHB · submitted 2022-03-31 · cs.CV · cs.LG

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EFA5WFHBrecord.jsonopen to challenge →

classification cs.CV cs.LG
keywords low-densityregionsdatasamplesdiffusionfidelitymodelsnovel
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.