基本信息
浏览量:161
职业迁徙
个人简介
My primary research focuses on making AI (specifically computer-vision based perception) robust, reliable, and safe. For this, we levarage strong generative models for finding systematic errors of image classifiers on rare subgroups and systematic errors of object detectors. We also identified vulnerabilities of Transformer-based neural network against adversarial patch/token attacks. To counteract such vulnerabilities, we developed architectures that are certifiably robust against patch attacks for image classifiers as well as for semantic segmentation. Furthermore, we proposed methods for adversarially training neural networks to become robust against universal perturbations and universal adversarial patches. In addition, we provide methods for test-time adaptation of neural networks to improve robustness to domain shifts and study the role of shape-biased representations on robustness to common image corruptions
研究兴趣
论文共 78 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW (2023): 4092-4101
arXiv (Cornell University) (2021)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn