DuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis

Name: DuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis
Uploaded: 2026-10-06T11:43:39.543636+00:00
Duration: 308 s
Description: DuetMoE addresses unfairness in medical image segmentation by tackling both inter-subgroup variation and intra-subgroup difficulty simultaneously. It uses a dual framework combining subgroup-aware distributionally robust optimization with a mixture-of-experts representation to ensure reliable predictions for every patient across different demographic groups.

DuetMoE addresses unfairness in medical image segmentation by tackling both inter-subgroup variation and intra-subgroup difficulty simultaneously. It uses a dual framework combining subgroup-aware distributionally robust optimization with a mixture-of-experts representation to ensure reliable predictions for every patient across different demographic groups.

Open the full episode