APAC

Reported on 2 benchmarks across 1 task · 1 paper

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

Computer Vision2 results

Image ClassificationonCIFAR-10
Percentage correct· 2015-05-13
89.7
best: 99.5 (ViT-H/14)
APAC: Augmented PAttern Classification with Neural Networks arXiv:1505.03229
Image ClassificationonMNIST
Percentage error· 2015-05-13
0.23
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
APAC: Augmented PAttern Classification with Neural Networks arXiv:1505.03229