GazeLT classifies long-tailed chest X-ray diseases by training a student model with a teacher that learns time-windowed radiologist gaze attention, improving tail-class accuracy on the NIH-CXR-LT and MIMIC-CXR-LT benchmarks.
Radiotransformer: a cascaded global-focal transformer for visual attention--guided disease classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs
GazeLT classifies long-tailed chest X-ray diseases by training a student model with a teacher that learns time-windowed radiologist gaze attention, improving tail-class accuracy on the NIH-CXR-LT and MIMIC-CXR-LT benchmarks.