Few-Shot Learning by Integrating Spatial and Frequency Representation
Open paper
Benchmark
Model
Rank
Results
few-shot-image-classification-on-cub-200-5-way-1-shot
PT+MAP+SF (transductive)
#4
Accuracy: 95.48
few-shot-image-classification-on-mini-imagenet-5-way-1-shot
PT+MAP (s+f) (transductive)
#8
Accuracy: 84.81
Rank counts only results with a code link.