SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

1 code implementation • 12 Dec 2022 • Wanqing Zhu, Jia-Li Yin, Bo-Hao Chen, Ximeng Liu

In this paper, we present a new meta self-training pipeline, named SRoUDA, for improving adversarial robustness of UDA models.

Adversarial Robustness Unsupervised Domain Adaptation

Universal Generative Modeling for Calibration-free Parallel Mr Imaging

1 code implementation • 25 Jan 2022 • Wanqing Zhu, Bing Guan, Shanshan Wang, Minghui Zhang, Qiegen Liu

The integration of compressed sensing and parallel imaging (CS-PI) provides a robust mechanism for accelerating MRI acquisitions.

Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness

no code implementations • 1 Dec 2021 • Jia-Li Yin, Lehui Xie, Wanqing Zhu, Ximeng Liu, Bo-Hao Chen

However, most of the existing adversarial training methods focus on improving the robust accuracy by strengthening the adversarial examples but neglecting the increasing shift between natural data and adversarial examples, leading to a dramatic decrease in natural accuracy.

Adversarial Robustness