most citedMEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2024★ 2 cited

MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization

Zhaozhe Hu, Jia-Li Yin, Bin Chen +3

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous resear…