SmoothNetV1

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

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

Computer Vision2 results

Image ClassificationonImagenette
Accuracy· 2022-05-09
69.7
best: 100 (µ2Net+ (ViT-L/16))
SOTA
SmoothNets: Optimizing CNN architecture design for differentially private deep learning arXiv:2205.04095
Image ClassificationonCIFAR-10
Percentage correct· 2022-05-09
73.5
best: 99.5 (ViT-H/14)
SmoothNets: Optimizing CNN architecture design for differentially private deep learning arXiv:2205.04095