On First-Order Meta-Learning Algorithms

Benchmark Model Rank Results
few-shot-image-classification-on-tiered-imagenet-10-way-1-shotReptile+BN#10Accuracy: 35.3
few-shot-image-classification-on-tiered-imagenet-10-way-1-shotReptile#13Accuracy: 33.7
few-shot-image-classification-on-mini-imagenet-10-way-1-shotReptile+BN#11Accuracy: 32.0
few-shot-image-classification-on-mini-imagenet-10-way-1-shotReptile#14Accuracy: 31.1
few-shot-image-classification-on-mini-imagenet-10-way-5-shotReptile+BN#12Accuracy: 47.6
few-shot-image-classification-on-mini-imagenet-10-way-5-shotReptile#14Accuracy: 44.7
few-shot-image-classification-on-tiered-imagenet-10-way-5-shotReptile+BN#12Accuracy: 52.0
few-shot-image-classification-on-tiered-imagenet-10-way-5-shotReptile#13Accuracy: 48.0
few-shot-image-classification-on-omniglot-5-shot-5-wayReptile + Transduction#13Accuracy: 99.48
few-shot-image-classification-on-omniglot-1-shot-5-wayReptile + Transduction#16Accuracy: 97.68
few-shot-image-classification-on-omniglot-1-shot-20-wayReptile + Transduction#17Accuracy: 89.43%
few-shot-image-classification-on-omniglot-5-shot-20-wayReptile + Transduction#17Accuracy: 97.12%
few-shot-image-classification-on-mini-imagenet-5-way-5-shotReptile + Transduction#84Accuracy: 65.99
few-shot-image-classification-on-mini-imagenet-5-way-1-shotReptile + Transduction#92Accuracy: 49.97