PubMed2 min read
Uncertainty-suppressed long-tailed learning with lightweight feature adaptation for multi-label chest X-ray classification
CONCLUSIONS: USLFA improved macro-AUPRC and rare-label recognition without introducing an additional inference-time branch. Macro F1 was significantly higher than the principal BCE and LDAM baselines in the main comparison, whereas the additional macro F1 gain attributable to uncertainty…
By Lu LiPubMed - AI Research
Read the full story
Originally published by PubMed - AI Research on Oct 20, 2026.
Comments
Sign in to join the discussion.