PyramidNet + AA (AMP)

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· 2020-10-10
98.02
best: 99.5 (ViT-H/14)
Regularizing Neural Networks via Adversarial Model Perturbation arXiv:2010.04925
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2020-10-10
86.64
best: 96.08 (EffNet-L2 (SAM))
Regularizing Neural Networks via Adversarial Model Perturbation arXiv:2010.04925
Image ClassificationonSVHN
Percentage error· 2020-10-10
1.35
best: 1 (E2E-M3)
Regularizing Neural Networks via Adversarial Model Perturbation arXiv:2010.04925