AI RESEARCH

Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification

arXiv CS.CV

ArXi:2605.02292v1 Announce Type: new Chest X-ray classification suffers from severe class imbalance where gradient updates bias toward majority classes, causing feature drift and poor performance on rare but critical pathologies. We propose a Momentum-Anchored Multi-Scale Fusion Network that uses exponential moving averages (EMA) as a temporal anchoring mechanism to stabilize feature representations under long-tailed distributions.