no code implementations • ICML 2020 • Mingjie Li, Lingshen He, Zhouchen Lin
By viewing ResNet as an explicit Euler discretization of an ordinary differential equation (ODE), for the first time, we find that the adversarial robustness of ResNet is connected to the numerical stability of the corresponding dynamic system.
1 code implementation • NeurIPS 2021 • Lingshen He, Yuxuan Chen, Zhengyang Shen, Yiming Dong, Yisen Wang, Zhouchen Lin
Group equivariant CNNs (G-CNNs) that incorporate more equivariance can significantly improve the performance of conventional CNNs.
no code implementations • NeurIPS 2021 • Lingshen He, Yiming Dong, Yisen Wang, DaCheng Tao, Zhouchen Lin
Attention mechanism has shown great performance and efficiency in a lot of deep learning models, in which relative position encoding plays a crucial role.
3 code implementations • ICML 2020 • Zhengyang Shen, Lingshen He, Zhouchen Lin, Jinwen Ma
In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs).
Ranked #1 on Image Classification on MNIST-rot-12