LHCF trains medical image models for fairness by optimizing across latent appearance-based cohorts discovered via clustering, achieving SOTA results on single and multiple demographic attributes without using any demographic labels.
arXiv preprint arXiv:2411.11939 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PecMan is a fairness-aware human-AI cooperative classification framework for medical images that jointly handles subgroup reliability, decision allocation to AI or humans, and collaborative predictions, introducing the FairHAI benchmark and showing better trade-offs than separate approaches.
citing papers explorer
-
Fairness Beyond Demographics: Optimizing Performance Across Appearance-Based Hidden Cohorts in Medical Imaging
LHCF trains medical image models for fairness by optimizing across latent appearance-based cohorts discovered via clustering, achieving SOTA results on single and multiple demographic attributes without using any demographic labels.
-
People-Centred Medical Image Analysis via Fairness-Aware Human-AI Cooperation
PecMan is a fairness-aware human-AI cooperative classification framework for medical images that jointly handles subgroup reliability, decision allocation to AI or humans, and collaborative predictions, introducing the FairHAI benchmark and showing better trade-offs than separate approaches.