DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

Benchmark Model Rank Results
few-shot-image-classification-on-tiered-imagenet-5-way-5-shotDiffKendall (Meta-Baseline, ResNet-12)#28Accuracy: 85.31
few-shot-image-classification-on-tiered-imagenet-5-way-1-shotDiffKendall (Meta-Baseline, ResNet-12)#30Accuracy: 70.76
few-shot-image-classification-on-mini-imagenet-5-way-5-shotDiffKendall (Meta-Baseline, ResNet-12)#47Accuracy: 80.79
few-shot-image-classification-on-mini-imagenet-5-way-1-shotDiffKendall (Meta-Baseline, ResNet-12)#50Accuracy: 65.56