Few-shot classification on Cars cross-domain from tiered-ImageNet
59.01AccuracyProtoNet + SiMT
Evaluation Results
| Method | Links | |
|---|---|---|
| ProtoNet + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 59.01 | |
| MetaSGD + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 57.97 | |
| ProtoNetShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 57.23 | |
| MetaSGDShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 56.28 | |
| ANIL + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 54.6 | |
| MAML + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 51.88 | |
| MAMLShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 51.08 | |
| ANILShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 50.5 | |
| MetaSGD + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 38.69 | |
| MetaSGDShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 38.09 | |
| ProtoNet + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 38.07 | |
| ProtoNetShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 37.59 | |
| MAML + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 37.21 | |
| ANIL + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 36.92 | |
| MAMLShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 36.62 | |
| ANILShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 36.27 |