List your company
ResearchFormerly WizWand

Few-shot classification on Cars cross-domain from tiered-ImageNet

59.01AccuracyProtoNet + SiMT
35.360441.500247.6453.7798Oct 11, 2022
Updated 8mo ago

Evaluation results

MethodLinks
ProtoNet + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1059.01
MetaSGD + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1057.97
ProtoNetShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1057.23
MetaSGDShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1056.28
ANIL + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1054.6
MAML + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1051.88
MAMLShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1051.08
ANILShots=5-shot, Ways=5-way, Backbone=ResNet-122022.1050.5
MetaSGD + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1038.69
MetaSGDShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1038.09
ProtoNet + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1038.07
ProtoNetShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1037.59
MAML + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1037.21
ANIL + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1036.92
MAMLShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1036.62
ANILShots=1-shot, Ways=5-way, Backbone=ResNet-122022.1036.27