Image Classification on EuroSAT (Accuracy, CovGap, MCCC)
0.06CovGapAPS
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| APSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.06 | — | 0.83 | |
| L-APS (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.06 | — | 0.81 | |
| L-APSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.06 | — | 0.83 | |
| L-LACBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.07 | — | 0.75 | |
| TOPKBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.81 | |
| L-TOPKBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.76 | |
| RAPSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.72 | |
| LACBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.09 | — | 0.7 | |
| L-LAC (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.09 | — | 0.68 | |
| L-RAPS (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.09 | — | 0.71 | |
| L-TOPK (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.11 | — | 0.68 | |
| L-RAPSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.12 | — | 0.52 | |
| Zero-Shot AccuracyBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | — | 36.1 | — |