no code implementations • 20 Apr 2024 • Yuheng Ji, Yue Liu, Zhicheng Zhang, Zhao Zhang, YuTing Zhao, Gang Zhou, Xingwei Zhang, Xinwang Liu, Xiaolong Zheng
Different from LoRA, we improve the efficiency and robustness of adversarial adaptation by designing a novel reparameterizing method based on parameter clustering and parameter alignment.
no code implementations • 8 Mar 2023 • Jun Shi, Bingcai Wei, Gang Zhou, Liye Zhang
In this paper, we introduce an effective hybrid architecture for sand image restoration tasks, which leverages local features from CNN and long-range dependencies captured by transformer to improve the results further.
no code implementations • 25 Aug 2021 • Wei Niu, Zhengang Li, Xiaolong Ma, Peiyan Dong, Gang Zhou, Xuehai Qian, Xue Lin, Yanzhi Wang, Bin Ren
It necessitates the sparse model inference via weight pruning, i. e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy.
no code implementations • 24 Jun 2021 • Woosub Jung, Yizhou Feng, Sabbir Ahmed Khan, Chunsheng Xin, Danella Zhao, Gang Zhou
We also designed a distributed CNN classifier for online inference in a laboratory setting.
no code implementations • 16 Feb 2021 • Gang Zhou
In this paper we study a neighborhood of generic singularities formed by mean curvature flow (MCF).
Differential Geometry Analysis of PDEs 53C44, 35K93