Search Results for author: Shiji Xin

Found 4 papers, 2 papers with code

MEWL: Few-shot multimodal word learning with referential uncertainty

1 code implementation1 Jun 2023 Guangyuan Jiang, Manjie Xu, Shiji Xin, Wei Liang, Yujia Peng, Chi Zhang, Yixin Zhu

To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes.

On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization

no code implementations18 Dec 2022 Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang

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

Out-of-Distribution Generalization

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.