APT detects overfitting during diffusion fine-tuning and uses adaptive augmentation, loss weighting, feature-statistics regularization, and attention alignment to preserve prior knowledge while learning new concepts.
A neural space-time representation for text- to-image personalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
APT: Adaptive Personalized Training for Diffusion Models with Limited Data
APT detects overfitting during diffusion fine-tuning and uses adaptive augmentation, loss weighting, feature-statistics regularization, and attention alignment to preserve prior knowledge while learning new concepts.