Few Shot Image Classification On Cifar Fs 5 1
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| EASY 2xResNet12 1/√2 (transductive) | 90.2 | - | - |
| PT+MAP+SF+SOT (transductive) | 92.83 | - | - |
| Adaptive Subspace Network | 87.3 | - | - |
| BAVARDAGE | 90.63 | - | - |
| Multi-Task Learning | 84.1 | - | - |
| RCN - Conv4-64 | 77.63 | - | - |
| MTUNet+ResNet-18 | 80.16 | - | - |
| P>M>F (P=DINO-ViT-base, M=ProtoNet) | 92.2 | - | - |
| HCTransformers | 90.50 | - | - |
| MetaQDA | 88.79 | - | - |
| Invariance-Equivariance | 89.74 | - | - |
| FewTURE | 88.90 | - | - |
| CAML [Laion-2b] | 93.5 | - | - |
| MetaOptNet-SVM-trainval | 85 | - | - |
| EASY 3xResNet12 (transductive) | 90.47 | - | - |
| ICI | 84.32 | - | - |
| LST+MAP | 90.73 | - | - |
| EASY 3xResNet12 (inductive) | 89.0 | - | - |
| MTUNet+WRN | 82.93 | - | - |
| S2M2R | 87.47 | - | - |
0 of 39 row(s) selected.