Few-shot classification on Cars cross-domain from mini-ImageNet
51.67AccuracyProtoNet + SiMT
Evaluation Results
| Method | Links | |
|---|---|---|
| ProtoNet + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 51.67 | |
| MetaSGD + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 49.86 | |
| ProtoNetShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 48.06 | |
| MetaSGDShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 47.44 | |
| MAML + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 46.59 | |
| ANIL + SiMTShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 45.88 | |
| MAMLShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 44.56 | |
| ANILShots=5-shot, Ways=5-way, Backbone=ResNet-122022.10 | 41.65 | |
| ProtoNet + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 34.53 | |
| MetaSGDShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 34.52 | |
| MetaSGD + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 33.92 | |
| MAML + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 33.73 | |
| MAMLShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 32.87 | |
| ProtoNetShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 32.79 | |
| ANIL + SiMTShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 32.34 | |
| ANILShots=1-shot, Ways=5-way, Backbone=ResNet-122022.10 | 31.28 |