NiN+APL

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· 2014-12-21
92.5
best: 99.5 (ViT-H/14)
Learning Activation Functions to Improve Deep Neural Networks arXiv:1412.6830
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2014-12-21
69.2
best: 96.08 (EffNet-L2 (SAM))
Learning Activation Functions to Improve Deep Neural Networks arXiv:1412.6830