List your company
ResearchFormerly WizWand

5-way Few-Shot Classification on miniImageNet 5-way (meta-test)

76.5AccuracyMetaOptNet-SVM(+EHG)
49.584856.572463.5670.5476Feb 20, 2026
Updated 8mo ago

Evaluation results

MethodLinks
MetaOptNet-SVM(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0276.5
MetaOptNet-SVMshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0275.35
ProtoNet(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0274.94
MetaOptNet-RR(+EHG)shot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0274.94
MetaOptNet-RRshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0274.69
ProtoNetshot count=5-shot, backbone=ResNet-12, feature dimension=160002026.0273.8
ProtoNet(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0270.71
ProtoNetshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0270.06
MetaOptNet-SVM(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0269.69
MetaOptNet-SVMshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0269.67
MetaOptNet-RR(+EHG)shot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0269.61
MetaOptNet-RRshot count=5-shot, backbone=4-layer conv, feature dimension=16002026.0268.72
ProtoNet(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0259.27
MetaOptNet-RR(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0259.27
MetaOptNet-SVM(+EHG)shot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0258.2
MetaOptNet-SVMshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0258
MetaOptNet-RRshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0257.6
ProtoNetshot count=1-shot, backbone=ResNet-12, feature dimension=160002026.0257.38
MetaOptNet-RR(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0252.91
ProtoNet(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0252.71
MetaOptNet-SVM(+EHG)shot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0252.35
MetaOptNet-RRshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0251.67
MetaOptNet-SVMshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0250.84
ProtoNetshot count=1-shot, backbone=4-layer conv, feature dimension=16002026.0250.62