A combined logit-adjusted loss and CVaR objective improves macro F1 and reduces gender disparity in 3D CT classification of lung cancers, COVID-19, and normal cases on a benchmark with severe class and group imbalance.
Preserv- ing fairness generalization in deepfake detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A multi-task model with EfficientNet-B7 predicts COVID-19 and source center using logit-adjusted loss, achieving F1 0.9098 and AUC 0.9647 on 308 multi-center scans.
citing papers explorer
-
Robust Fair Disease Diagnosis in CT Images
A combined logit-adjusted loss and CVaR objective improves macro F1 and reduces gender disparity in 3D CT classification of lung cancers, COVID-19, and normal cases on a benchmark with severe class and group imbalance.
-
Robust Multi-Source Covid-19 Detection in CT Images
A multi-task model with EfficientNet-B7 predicts COVID-19 and source center using logit-adjusted loss, achieving F1 0.9098 and AUC 0.9647 on 308 multi-center scans.