Optimizes subclass priors in flow matching via latent GMM partitioning and conditioned sources to improve rare disease image generation fidelity, diversity, and downstream classification on long-tailed medical datasets.
In: ICLR’24 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flow Matching with Optimized Subclass Priors for Medical Image Augmentation
Optimizes subclass priors in flow matching via latent GMM partitioning and conditioned sources to improve rare disease image generation fidelity, diversity, and downstream classification on long-tailed medical datasets.