R-Mix (PreActResNet-18)

Reported on 2 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology1 result

ClassificationonCIFAR-100
Expected Calibration Error· 2022-12-09
3.73
SOTA
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding arXiv:2212.04875

Computer Vision1 result

Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2022-12-09
81.49
best: 96.08 (EffNet-L2 (SAM))
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding arXiv:2212.04875