5-way Few-Shot Classification on miniImageNet 5-way (meta-test)
76.5AccuracyMetaOptNet-SVM(+EHG)
Evaluation Results
| Method | Links | |
|---|---|---|
| MetaOptNet-SVM(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 76.5 | |
| MetaOptNet-SVMshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 75.35 | |
| ProtoNet(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 74.94 | |
| MetaOptNet-RR(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 74.94 | |
| MetaOptNet-RRshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 74.69 | |
| ProtoNetshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.02 | 73.8 | |
| ProtoNet(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 70.71 | |
| ProtoNetshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 70.06 | |
| MetaOptNet-SVM(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 69.69 | |
| MetaOptNet-SVMshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 69.67 | |
| MetaOptNet-RR(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 69.61 | |
| MetaOptNet-RRshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.02 | 68.72 | |
| ProtoNet(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 59.27 | |
| MetaOptNet-RR(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 59.27 | |
| MetaOptNet-SVM(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 58.2 | |
| MetaOptNet-SVMshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 58 | |
| MetaOptNet-RRshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 57.6 | |
| ProtoNetshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.02 | 57.38 | |
| MetaOptNet-RR(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 52.91 | |
| ProtoNet(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 52.71 | |
| MetaOptNet-SVM(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 52.35 | |
| MetaOptNet-RRshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 51.67 | |
| MetaOptNet-SVMshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 50.84 | |
| ProtoNetshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.02 | 50.62 |