TextCaps : Handwritten Character Recognition with Very Small Datasets

Open paper
Benchmark Model Rank Results
image-classification-on-emnist-lettersTextCaps#6Accuracy: 95.39
image-classification-on-fashion-mnistTextCaps#8Percentage error: 6.29
image-classification-on-mnistTextCaps#14Percentage error: 0.29Accuracy: 99.71

Rank counts only results with a code link.