no code implementations • 27 May 2024 • Hongtao Wang, Rongyu Feng, Liangyi Wu, Mutian Liu, Yinuo Cui, Chunxia Zhang, Zhenbo Guo
However, current designed segmentation networks is difficult to ensure the horizontal continuity of the segmentation.
no code implementations • 12 Apr 2024 • Hongtao Wang, Li Long, Jiangshe Zhang, Xiaoli Wei, Chunxia Zhang, Zhenbo Guo
Addressing this, we propose a novel approach using deep graph learning called DGL-FB, constructing a large graph to efficiently extract information.
no code implementations • 29 Feb 2024 • Fangyuan Zhang, Huichi Zhou, Shuangjiao Li, Hongtao Wang
Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks.
no code implementations • 11 Sep 2023 • Yue Li, Junru Li, Chaoyi Lin, Kai Zhang, Li Zhang, Franck Galpin, Thierry Dumas, Hongtao Wang, Muhammed Coban, Jacob Ström, Du Liu, Kenneth Andersson
The past decade has witnessed the huge success of deep learning in well-known artificial intelligence applications such as face recognition, autonomous driving, and large language model like ChatGPT.
no code implementations • 9 Jul 2023 • Xiaoli Wei, Chunxia Zhang, Hongtao Wang, Chengli Tan, Deng Xiong, Baisong Jiang, Jiangshe Zhang, Sang-Woon Kim
The model training is established on the denoising diffusion probabilistic model, where U-Net is equipped with the multi-head self-attention to match the noise in each step.
no code implementations • 23 May 2023 • Hongtao Wang, Jiangshe Zhang, Xiaoli Wei, Li Long, Chunxia Zhang
Many deep neural networks (DNNs)-based automatic picking methods have been proposed to accelerate this processing.
no code implementations • 16 Sep 2022 • Xinlin Leng, Chenxu Li, Weifeng Xu, Yuyan Sun, Hongtao Wang
We show that the FCD scheme fills the gap of multiparty secure Coordinate Descent methods and is applicable for general linear regressions, including linear, ridge and lasso regressions.
no code implementations • 7 Sep 2022 • Hongtao Wang, Jiangshe Zhang, Xiaoli Wei, Chunxia Zhang, Zhenbo Guo, Li Long, Yicheng Wang
Besides, since the gather data is a set of signals which are greatly different from the natural images, it is difficult for the current method to solve the FAT picking problem in case of a low Signal to Noise Ratio (SNR).
1 code implementation • 1 Jan 2022 • Yecheng Shao, Yongbin Jin, Xianwei Liu, Weiyan He, Hongtao Wang, Wei Yang
Reinforcement learning has become a powerful tool to formulate controllers for legged robots.
no code implementations • IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, VOL. 70, 2021 2020 • Hongtao Wang, Linfeng Xu, Anastasios Bezerianos, Chuangquan Chen, Zhiguo Zhang
Finally, the critical brain regions and connections for driving fatigue detection were investigated through the dynamically learned adjacency matrix. Index Terms— Attention-based multiscale convolutional neural network (CNN), driving fatigue, dynamical graph convolution network (GCN), electroencephalography (EEG), spatiotemporalstructure.
1 code implementation • 1 May 2020 • Zhao-Yang Wang, Hongtao Wang
The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions.