CKN

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision3 results

Image ClassificationonSTL-10
Percentage correct· 2014-06-12
62.3
best: 99.64 (µ2Net+ (ViT-L/16))
SOTA
Convolutional Kernel Networks arXiv:1406.3332
Image ClassificationonCIFAR-10
Percentage correct· 2014-06-12
82.2
best: 99.5 (ViT-H/14)
Convolutional Kernel Networks arXiv:1406.3332
Image ClassificationonMNIST
Percentage error· 2014-06-12
0.4
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Convolutional Kernel Networks arXiv:1406.3332