Adversarially optimized text embeddings re-trigger supposedly removed memorized images in pruned diffusion models, showing memorization is distributed rather than local.
SolidMark: Evaluating Image Memorization in Generative Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recent works have shown that diffusion models are able to memorize training images and emit them at generation time. However, the metrics used to evaluate memorization and its mitigation techniques suffer from dataset-dependent biases and struggle to detect whether a given specific image has been memorized or not. This paper begins with a comprehensive exploration of issues surrounding memorization metrics in diffusion models. Then, to mitigate these issues, we introduce $\rm \style{font-variant: small-caps}{SolidMark}$, a novel evaluation method that provides a per-image memorization score. We then re-evaluate existing memorization mitigation techniques. We also show that $\rm \style{font-variant: small-caps}{SolidMark}$ is capable of evaluating fine-grained pixel-level memorization. Finally, we release a variety of models based on $\rm \style{font-variant: small-caps}{SolidMark}$ to facilitate further research for understanding memorization phenomena in generative models. All of our code is available at https://github.com/NickyDCFP/SolidMark.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Finding DoRI: Discovery of Retained Images in Diffusion Models
Adversarially optimized text embeddings re-trigger supposedly removed memorized images in pruned diffusion models, showing memorization is distributed rather than local.