Multi-instance Learning Classification on MUSK2 classical MIL (10-fold cross-validation)
97AccuracyTR-RGMIL
Evaluation results
| Method | Links | |
|---|---|---|
| TR-RGMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 97 | |
| PSMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 96.4 | |
| ConveyanceEvaluation Protocol=10-fold CV, Runs=5 runs, Design=default parameters and no MIL-specific design choices2026.05 | 94 | |
| DSMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 93 | |
| DPMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 92.6 | |
| RGMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 92 | |
| BDRMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 90.5 | |
| Gated-ABMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 86.3 | |
| ABMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 85.8 |