Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

Benchmark Model Rank Results
few-shot-image-classification-on-mini-imagenet-cub-5-way-1-shotFEAT (Ye et al., 2018)#10Accuracy: 39.00
few-shot-image-classification-on-cub-200-5-way-5-shotfeat (ProtoNet)#26Accuracy: 83.03
few-shot-image-classification-on-cub-200-5-way-1-shotfeat (ProtoNet)#28Accuracy: 68.65
few-shot-image-classification-on-mini-imagenet-5-way-5-shotfeat+ (ProtoNet-ResNet)#55Accuracy: 78.38
few-shot-image-classification-on-mini-imagenet-5-way-1-shotfeat+ (ProtoNet-ResNet)#64Accuracy: 61.72