Uncertainty in Model-Agnostic Meta-Learning using Variational Inference

Benchmark Model Rank Results
few-shot-image-classification-on-omniglot-1-shot-5-wayVAMPIRE#11Accuracy: 98.43
few-shot-image-classification-on-omniglot-5-shot-5-wayVAMPIRE#11Accuracy: 99.56%
few-shot-image-classification-on-omniglot-5-shot-20-wayVAMPIRE#12Accuracy: 98.52%
few-shot-image-classification-on-omniglot-1-shot-20-wayVAMPIRE#16Accuracy: 93.2
few-shot-image-classification-on-tiered-imagenet-5-way-1-shotVAMPIRE#31Accuracy: 69.87
few-shot-image-classification-on-tiered-imagenet-5-way-5-shotVAMPIRE#34Accuracy: 82.7
few-shot-image-classification-on-mini-imagenet-5-way-5-shotVAMPIRE#85Accuracy: 64.31
few-shot-image-classification-on-mini-imagenet-5-way-1-shotVAMPIRE#87Accuracy: 51.54