List your company
ResearchFormerly WizWand

Few-shot classification on Cars

75.15AccuracySupervised
29.639641.454853.2765.0852Jan 23, 2020Jul 30, 2020Feb 4, 2021Aug 12, 2021Feb 17, 2022Aug 25, 2022Mar 2, 2023
Updated 8mo ago

Evaluation results

MethodLinks
SupervisedBackbone=ResNet-50, Evaluation protocol=5-way 5-shot2023.0375.15——
PsCoway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0357.5——
PsCoBackbone=ResNet-50, Base Method=BYOL, Evaluation protocol=5-way 5-shot2023.0356.19——
PsCoBackbone=ResNet-50, Base Method=MoCo v2, Evaluation protocol=5-way 5-shot2023.0353.45——
MoCo v2way=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0351.77——
PsCoBackbone=ResNet-18, Base Method=MoCo v2, Evaluation protocol=5-way 5-shot2023.0350.73——
SimCLRway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0350.05——
SWAVway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0350.03——
MAMLway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0348.82——
ProtoNetsway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0347.98——
MoCo v2Backbone=ResNet-50, Evaluation protocol=5-way 5-shot2023.0347.67——
MoCo v2Backbone=ResNet-18, Evaluation protocol=5-way 5-shot2023.0346.42——
Meta-SVEBMway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0346.23——
MetaOptNet-SVM-trainvalBackbone=ResNet-12, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=false2020.0145.9——
BYOLBackbone=ResNet-50, Evaluation protocol=5-way 5-shot2023.0345.74——
GNN (FT)Backbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=true2020.0144.9——
GNNBackbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=false2020.0144.28——
PsCoway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0344.01——
MatchingNet (FT)Backbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=true2020.0141.24——
MAMLway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0341.17——
RelationNet (FT)Backbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=true2020.0139.91——
MatchingNetBackbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=false2020.0138.99——
ProtoNetsway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0338.98——
MoCo v2way=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0338.65——
Meta-GMVAEway=5, shot=20, Backbone=Conv5, Pre-trained=miniImageNet2023.0338.36——
SimCLRway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0337.4——
RelationNetBackbone=ResNet-10, Training Dataset=mini-ImageNet, FT (Feature-wise Transformation)=false2020.0137.33——
SWAVway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0336.85——
Meta-SVEBMway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0334.27——
Meta-GMVAEway=5, shot=5, Backbone=Conv5, Pre-trained=miniImageNet2023.0331.39——
GNNTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—31.7243.7
GNN + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04—33.6149.14
GNN + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—32.2546.19
GNN + LRPTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—31.4646.07
RelationNetTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—30.0940.46
RelationNet + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04—31.7942.95
RelationNet + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—30.4540.18
RelationNet + LRPTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—30.4841.21
TPNTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—32.4244.54
TPN + ATATraining dataset=mini-ImageNet, Number of ways=5-way2021.04—34.1846.95
TPN + FTTraining dataset=mini-ImageNet, Number of ways=5-way2021.04—26.534.03