5-way 3-shot Image Classification on MiniImageNet 0% noise 54 (test)
64.28AccuracyTraNFS-3
Evaluation results
| Method | Links | |
|---|---|---|
| TraNFS-3Layers=32022.04 | 64.28 | |
| TraNFS-2Layers=22022.04 | 64.17 | |
| Cosine T = 0.2Distance Metric=Cosine, Temperature (T)=0.22022.04 | 62.75 | |
| Absolute T = 50.0Distance Metric=Absolute, Temperature (T)=50.02022.04 | 62.69 | |
| Cosine T = 2.0Distance Metric=Cosine, Temperature (T)=2.02022.04 | 62.63 | |
| Euclidean T = 25.0Distance Metric=Euclidean, Temperature (T)=25.02022.04 | 62.62 | |
| Euclidean T = 50.0Distance Metric=Euclidean, Temperature (T)=50.02022.04 | 62.62 | |
| Oracle2022.04 | 62.6 | |
| MedianType=Spatial median prototypes2022.04 | 62.6 | |
| Euclidean T = 10.0Distance Metric=Euclidean, Temperature (T)=10.02022.04 | 62.58 | |
| RNNP2022.04 | 62.57 | |
| Cosine T = 0.5Distance Metric=Cosine, Temperature (T)=0.52022.04 | 62.55 | |
| Vanilla ProtoNet2022.04 | 62.54 | |
| Absolute T = 25.0Distance Metric=Absolute, Temperature (T)=25.02022.04 | 62.54 | |
| Cosine T = 5.0Distance Metric=Cosine, Temperature (T)=5.02022.04 | 62.54 | |
| Cosine T = 1.0Distance Metric=Cosine, Temperature (T)=1.02022.04 | 62.52 | |
| Absolute T = 10.0Distance Metric=Absolute, Temperature (T)=10.02022.04 | 61.77 | |
| Linear Classifier2022.04 | 61.54 | |
| MAML2022.04 | 59.79 | |
| Matching Networks2022.04 | 57.86 | |
| Nearest kk=12022.04 | 52.98 | |
| Nearest kk=32022.04 | 50.59 | |
| Nearest kk=52022.04 | 50.2 |