SKNet-29 (ResNeXt-29, 16×32d)

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· 2019-03-15
96.53
best: 99.5 (ViT-H/14)
Selective Kernel Networks arXiv:1903.06586
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2019-03-15
82.67
best: 96.08 (EffNet-L2 (SAM))
Selective Kernel Networks arXiv:1903.06586