A new benchmark dataset of 456 real rare-disease face images demonstrates that phenotype-aware synthetic augmentation with landmark filtering improves AI diagnostic accuracy by up to 13.7% in ultra-low-data regimes.
Efros, Eli Shecht- man, and Oliver Wang
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
RetinexDualV2 introduces a physically-grounded dual Retinex architecture with task-specific priors and conditioned attention to unify UHD image restoration across rain, low-light, and noise degradations.
citing papers explorer
-
RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
A new benchmark dataset of 456 real rare-disease face images demonstrates that phenotype-aware synthetic augmentation with landmark filtering improves AI diagnostic accuracy by up to 13.7% in ultra-low-data regimes.
-
RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration
RetinexDualV2 introduces a physically-grounded dual Retinex architecture with task-specific priors and conditioned attention to unify UHD image restoration across rain, low-light, and noise degradations.