Image Classification on SUN397 (Accuracy, CovGap, MCCC)
0.08CovGapTOPK
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TOPKBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| L-TOPK (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| L-TOPKBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| LACBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.02 | |
| L-LAC (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| L-LACBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| APSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.09 | |
| L-APS (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.09 | |
| L-APSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.09 | |
| RAPSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| L-RAPS (naive)Backbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| L-RAPSBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | 0.08 | — | 0.03 | |
| Zero-Shot AccuracyBackbone=RN50, Alpha=0.1, Number of folds=102026.06 | — | 58.8 | — |