List your company
ResearchFormerly WizWand

Few-shot Classification on CUB200 5-way 1-shot

95.8AccuracyPTMAP-SF-SOTp
35.292851.001466.7182.4186Aug 11, 2021Sep 19, 2021Oct 29, 2021Dec 8, 2021Jan 16, 2022Feb 25, 2022Apr 6, 2022
Updated 8mo ago

Evaluation results

MethodLinks
PTMAP-SF-SOTpSOT insertion=without network retraining2022.0495.8
PTMAP-SF(S)2022.0495.45
Sill-Net-SOTpSOT insertion=without network retraining2022.0494.86
Sill-Net(S)2022.0494.73
Our Method (Improved EM)Setting=Transductive2021.0893.78
Conference VersionSetting=Transductive2021.0893.2
Our Method (EM)Setting=Transductive2021.0892.35
PTMAP-SOTpSOT insertion=without network retraining2022.0491.9
PTMAP(S)2022.0491.55
Our MethodSetting=Inductive2021.0888.99
ICISetting=Transductive2021.0887.87
BD-CSPNSetting=Transductive2021.0884.9
RAP-LaplacianShotSetting=Transductive2021.0883.59
EPNetSetting=Transductive2021.0882.85
TIM-GDSetting=Transductive2021.0882.2
LaplacianShotSetting=Transductive2021.0880.96
CPDESetting=Inductive2021.0880.11
DCSetting=Inductive2021.0877.22
SRestoreNetSetting=Transductive2021.0876.85
MultiSemSetting=Inductive2021.0876.1
RAP-ProtoNetSetting=Inductive2021.0875.17
RestoreNetSetting=Inductive2021.0874.32
CentAlignSetting=Inductive2021.0874.22
CFASetting=Inductive2021.0873.9
Neg-CosineSetting=Inductive2021.0872.66
MAMLSetting=Inductive2021.0855.92
SimSiam + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1148.08
Supervised + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1147.58
SupervisedBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1146.57
SimSiamBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1145.56
MoCo v2 + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1144.17
MoCo v2Backbone=ResNet-50, Pre-training Dataset=ImageNet1002021.1141.67
SimSiam + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.1141.6
MoCo v2 + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.1138.33
SimSiamBackbone=ResNet-18, Pre-training Dataset=STL102021.1137.97
MoCo v2Backbone=ResNet-18, Pre-training Dataset=STL102021.1137.62