no code implementations • 26 May 2023 • Zhiyi Xue, Si Liu, Zhaodi Zhang, Yiting Wu, Min Zhang
In this paper, we study existing approaches and identify a dominant factor in defining tight approximation, namely the approximation domain of the activation function.
1 code implementation • CVPR 2023 • Zhaodi Zhang, Zhiyi Xue, Yang Chen, Si Liu, Yueling Zhang, Jing Liu, Min Zhang
Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training.
no code implementations • 21 Nov 2022 • Yiting Wu, Zhaodi Zhang, Zhiyi Xue, Si Liu, Min Zhang
We observe that existing approaches only rely on overestimated domains, while the corresponding tight approximation may not necessarily be tight on its actual domain.