Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification
Open paper
Benchmark
Model
Rank
Results
graph-property-prediction-on-ogbg-molhiv
DeepAUC
#1
Test ROC-AUC: 0.8352 ± 0.0054
Ext. data: No
…
multi-label-classification-on-chexpert
DeepAUC-v1
#3
AVERAGE AUC ON 14 LABEL: 0.930
NUM RADS BELOW CURVE: 2.800
Rank counts only results with a code link.