Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning

Benchmark Model Rank Results
few-shot-image-classification-on-cifar-fs-5Invariance-Equivariance#15Accuracy: 77.87
few-shot-image-classification-on-cifar-fs-5-1Invariance-Equivariance#12Accuracy: 89.74
few-shot-image-classification-on-fc100-5-wayInvariance-Equivariance#9Accuracy: 47.76
few-shot-image-classification-on-fc100-5-way-1Invariance-Equivariance#7Accuracy: 65.3
few-shot-image-classification-on-meta-datasetInvariance-Equivariance#13Accuracy: 68.89
few-shot-image-classification-on-mini-2Invariance-Equivariance#43Accuracy: 67.28
few-shot-image-classification-on-mini-3Invariance-Equivariance#23Accuracy: 84.78
few-shot-image-classification-on-tieredInvariance-Equivariance#25Accuracy: 72.21
few-shot-image-classification-on-tiered-1Invariance-Equivariance#20Accuracy: 87.08