Multi-instance Learning Classification on ELEPHANT classical MIL (10-fold cross-val)
94.3AccuracyConveyance
Evaluation results
| Method | Links | |
|---|---|---|
| ConveyanceEvaluation Protocol=10-fold CV, Runs=5 runs, Design=default parameters and no MIL-specific design choices2026.05 | 94.3 | |
| TR-RGMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 94.1 | |
| DSMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 92.5 | |
| PSMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 91.8 | |
| RGMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 91.5 | |
| BDRMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 90.8 | |
| DPMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 89.4 | |
| ABMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 86.8 | |
| Gated-ABMILEvaluation Protocol=10-fold CV, Runs=5 runs2026.05 | 85.7 |