A discriminator trained to distinguish clean from corrupt image-label pairs can be used during sampling to correct the score of a noisy-label conditional diffusion model, improving class-wise fidelity without retraining.
Denoising likelihood score match- ing for conditional score-based data generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction
A discriminator trained to distinguish clean from corrupt image-label pairs can be used during sampling to correct the score of a noisy-label conditional diffusion model, improving class-wise fidelity without retraining.