Multi-Instance Learning TPAUC Maximization on Lung (test)
0.865Mean TPAUCSONT (att)
Evaluation Results
| Method | Links | |
|---|---|---|
| SONT (att)(TPR lower bound, FPR upper bound)=(0.1, 0.9), Pooling strategy=attention-based2023.10 | 0.865 | |
| SOTAS (att)(TPR lower bound, FPR upper bound)=(0.1, 0.9), Pooling strategy=attention-based2023.10 | 0.841 | |
| MIDAM (smx)(TPR lower bound, FPR upper bound)=(0.1, 0.9), Pooling strategy=stochastic smoothed-max2023.10 | 0.824 | |
| MIDAM (att)(TPR lower bound, FPR upper bound)=(0.1, 0.9), Pooling strategy=attention-based2023.10 | 0.815 | |
| SONT (att)(TPR lower bound, FPR upper bound)=(0.3, 0.7), Pooling strategy=attention-based2023.10 | 0.779 | |
| SOTAS (att)(TPR lower bound, FPR upper bound)=(0.3, 0.7), Pooling strategy=attention-based2023.10 | 0.745 | |
| AUC-M (att)(TPR lower bound, FPR upper bound)=(0.1, 0.9), Pooling strategy=attention-based2023.10 | 0.744 | |
| MIDAM (att)(TPR lower bound, FPR upper bound)=(0.3, 0.7), Pooling strategy=attention-based2023.10 | 0.716 | |
| MIDAM (smx)(TPR lower bound, FPR upper bound)=(0.3, 0.7), Pooling strategy=stochastic smoothed-max2023.10 | 0.68 | |
| SONT (att)(TPR lower bound, FPR upper bound)=(0.5, 0.5), Pooling strategy=attention-based2023.10 | 0.639 | |
| AUC-M (att)(TPR lower bound, FPR upper bound)=(0.3, 0.7), Pooling strategy=attention-based2023.10 | 0.609 | |
| MIDAM (att)(TPR lower bound, FPR upper bound)=(0.5, 0.5), Pooling strategy=attention-based2023.10 | 0.544 | |
| SOTAS (att)(TPR lower bound, FPR upper bound)=(0.5, 0.5), Pooling strategy=attention-based2023.10 | 0.539 | |
| MIDAM (smx)(TPR lower bound, FPR upper bound)=(0.5, 0.5), Pooling strategy=stochastic smoothed-max2023.10 | 0.43 | |
| AUC-M (att)(TPR lower bound, FPR upper bound)=(0.5, 0.5), Pooling strategy=attention-based2023.10 | 0.32 |