Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning

Benchmark Model Rank Results
few-shot-image-classification-on-stanford-cars-5-way-1-shotDN4-DA (k=1)#1Accuracy: 61.51
few-shot-image-classification-on-stanford-cars-5-way-5-shotDN4-DA (k=1)#1Accuracy: 89.6
few-shot-image-classification-on-stanford-dogs-5-way-5-shotDN4-DA (k=1)#1Accuracy: 66.33
few-shot-image-classification-on-cub-200-5-way-5-shotDN4-DA (k=1)#27Accuracy: 81.9
few-shot-image-classification-on-cub-200-5-way-1-shotDN4-DA (k=1)#32Accuracy: 53.15
few-shot-image-classification-on-mini-imagenet-5-way-5-shotDN4 (k=3)#74Accuracy: 71.02
few-shot-image-classification-on-mini-imagenet-5-way-1-shotDN4 (k=3)#88Accuracy: 51.24