Search Results for author: Shiji Xin

Found 2 papers, 1 papers with code

Domain-wise Adversarial Training for Out-of-Distribution Generalization

no code implementations29 Sep 2021 Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang

Extensive experiments show that our proposed DAT can effectively remove the domain-varying features and improve OOD generalization on both correlation shift and diversity shift tasks.

Out-of-Distribution Generalization

Boosting Certified $\ell_\infty$ Robustness with EMA Method and Ensemble Model

2 code implementations1 Jul 2021 Binghui Li, Shiji Xin, Qizhe Zhang

Moreover, we give the theoretical analysis of the ensemble method based on the $1$-Lipschitz property on the certified robustness, which ensures the effectiveness and stability of the algorithm.

Cannot find the paper you are looking for? You can Submit a new open access paper.