no code implementations • 25 Jan 2024 • Minglin Chen, Weihao Yuan, Yukun Wang, Zhe Sheng, Yisheng He, Zilong Dong, Liefeng Bo, Yulan Guo
We propose a novel synchronized generation and reconstruction method to effectively optimize the NeRF.
no code implementations • 17 Jan 2022 • Yimin Huang, Xinyu Feng, Wanwan Wang, Hao He, Yukun Wang, Ming Yao
In most VFL frameworks, to protect the security and privacy of the participants' local data, a third party is needed to generate homomorphic encryption key pairs and perform decryption operations.
no code implementations • 1 Jan 2021 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang
We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.
no code implementations • 21 Oct 2020 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang
For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.