TextCaps

Reported on 5 benchmarks across 1 task · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision5 results

Image ClassificationonEMNIST-Letters
Accuracy· 2019-04-17
95.39
best: 95.96 (WaveMixLite-112/16)
SOTA
TextCaps : Handwritten Character Recognition with Very Small Datasets arXiv:1904.08095
Image ClassificationonEMNIST-Balanced
Accuracy· 2017-10-26
90.46
best: 91.48 (EMNIST-mobile)
SOTA
Dynamic Routing Between Capsules arXiv:1710.09829
Image ClassificationonFashion-MNIST
Percentage error· 2019-04-17
6.29
best: 3.64 (PreAct-ResNet18 + FMix)
TextCaps : Handwritten Character Recognition with Very Small Datasets arXiv:1904.08095
Image ClassificationonMNIST
Accuracy· 2019-04-17
99.71
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
TextCaps : Handwritten Character Recognition with Very Small Datasets arXiv:1904.08095
Image ClassificationonMNIST
Percentage error· 2019-04-17
0.29
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
TextCaps : Handwritten Character Recognition with Very Small Datasets arXiv:1904.08095