Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

Benchmark Model Rank Results
few-shot-image-classification-on-omniglot-1-1APL#8Accuracy: 97.2%
few-shot-image-classification-on-omniglot-1-2APL#15Accuracy: 97.9
few-shot-image-classification-on-omniglot-5-1APL#16Accuracy: 97.6%
few-shot-image-classification-on-omniglot-5-2APL#3Accuracy: 99.9