OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-10
OrthCaps-S
–
Percentage correct: 86.84
image-classification-on-cifar-100
OrthCaps-D
–
Percentage correct: 70.56
image-classification-on-mnist
OrthCaps-S
–
Accuracy: 99.68
Rank counts only results with a code link.