The authors treat each denoiser D_σ of a diffusion model as a self-map x_{k+1}=D_σ(x_k).
Memorization in diffusion models measured by persistence across noise scales
The authors define a critical noise scale that detects duplicated, overfitted, and outlier examples in trained models.
Top University
Cristina López Amado · Marco Fumero · Francesco Locatello
Institute of Science and Technology Austria (ISTA)
Research Digest··2 min read
López Amado et al.
Why this paper
From Institute of Science and Technology Austria (ISTA)
In one line
Diffusion models' fixed-scale denoiser dynamics reveal memorization through a critical noise scale.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§