CMsC

Reported on 4 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 Vision4 results

Image ClassificationonCIFAR-10
Percentage correct· 2015-11-18
93.1
best: 99.5 (ViT-H/14)
Competitive Multi-scale Convolution arXiv:1511.05635
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2015-11-18
72.4
best: 96.08 (EffNet-L2 (SAM))
Competitive Multi-scale Convolution arXiv:1511.05635
Image ClassificationonMNIST
Percentage error· 2015-11-18
0.3
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Competitive Multi-scale Convolution arXiv:1511.05635
Image ClassificationonSVHN
Percentage error· 2015-11-18
1.8
best: 1 (E2E-M3)
Competitive Multi-scale Convolution arXiv:1511.05635