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

Open paper
Benchmark Model Rank Results
few-shot-image-classification-on-mini-2DiffKendall (Meta-Baseline, ResNet-12)#49Accuracy: 65.56
few-shot-image-classification-on-mini-3DiffKendall (Meta-Baseline, ResNet-12)#46Accuracy: 80.79
few-shot-image-classification-on-tieredDiffKendall (Meta-Baseline, ResNet-12)#30Accuracy: 70.76
few-shot-image-classification-on-tiered-1DiffKendall (Meta-Baseline, ResNet-12)#28Accuracy: 85.31

Rank counts only results with a code link.