Cross-window knowledge distillation raises per-window AUC by 10-16 points in pulmonary CT by transferring latent pathological signatures from a teacher encoder on the most informative window to students on other windows.
High performance with fewer labels using semi-weakly supervised learning for pulmonary embolism diagnosis.NPJ Digit Med, 8(1):254
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge Distillation
Cross-window knowledge distillation raises per-window AUC by 10-16 points in pulmonary CT by transferring latent pathological signatures from a teacher encoder on the most informative window to students on other windows.