Mixed Classifier

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

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

Adversarial2 results

Adversarial RobustnessonCIFAR-100
AutoAttacked Accuracy· uses extra data· 2023-01-29
38.72
SOTA
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing arXiv:2301.12554
Adversarial RobustnessonCIFAR-100
Clean Accuracy· uses extra data· 2023-01-29
85.21
SOTA
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing arXiv:2301.12554