A two-part training regularizer, an unconditional-only contrastive repulsion plus a large-timestep conditional-unconditional alignment, improves tail-class diversity and fidelity in diffusion models, cutting ImageNet-LT FID from 19.9 to 15.1.
In: International Conference on Artificial Intelligence and Statistics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model
A two-part training regularizer, an unconditional-only contrastive repulsion plus a large-timestep conditional-unconditional alignment, improves tail-class diversity and fidelity in diffusion models, cutting ImageNet-LT FID from 19.9 to 15.1.