Image Classification on AIforCOVID v1 (test)
0.607G-MeanReal
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| RealTraining Data=Real, Backbone=ResNet182025.03 | 0.607 | — | — | |
| Single (top-1)Selection strategy=top-1 ranking, Ranking source=Real test set performance, Backbone=ResNet182025.03 | 0.588 | -3.1 | 1 | |
| G*Selection strategy=G* (Proposed Ensemble Selection), Backbone=ResNet182025.03 | 0.573 | -5.6 | 30 | |
| G* (Oracle)Selection strategy=G* Oracle Selection, Backbone=ResNet182025.03 | 0.573 | -5.6 | 30 | |
| Single (top-5)Selection strategy=top-5 ranking, Ranking source=Real test set performance, Backbone=ResNet182025.03 | 0.555 | -8.6 | 1 | |
| Naive (R)Selection strategy=Naive Random Ensemble, Backbone=ResNet182025.03 | 0.533 | -12.2 | 30 | |
| Naive (A)Selection strategy=Naive All Ensemble, Backbone=ResNet182025.03 | 0.487 | -19.8 | 110 | |
| Single (average)Selection strategy=average of single GANs, Backbone=ResNet182025.03 | 0.339 | -44.2 | 1 |