Reproduce “Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Duy Hoang Khuong, Duy Nguyen Huu, Ngu Huynh Cong Viet
The method combines a slowly updated copy of a late EfficientNetV2-S backbone block with multi-scale convolutional features to classify 14 chest X-ray diseases. On ChestX-ray14, it reports a mean AUC of 0.8682, compared with 0.85433 for SynthEnsemble, and the highest AUC in 13 disease categories. Infiltration is the exception; the comparison is not a controlled, matched re-run.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.