SimpleNetv1

Reported on 3 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 Vision3 results

Image ClassificationonCIFAR-10
Percentage correct· 2016-08-22
95.51
best: 99.5 (ViT-H/14)
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures arXiv:1608.06037
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2016-08-22
78.37
best: 96.08 (EffNet-L2 (SAM))
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures arXiv:1608.06037
Image ClassificationonMNIST
Percentage error· 2016-08-22
0.25
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures arXiv:1608.06037