no code implementations • 29 Apr 2024 • Yuxuan Yan, Shunpu Tang, Zhiguo Shi, Qianqian Yang
However, we observe that the non-IID data in federated learning leads to a gap in performance between the PEFT method and full parameter fine-tuning(FFT).
no code implementations • 20 Mar 2024 • Chaoqun Yang, Mengdie Xu, Xiaowei Liang, Zhiguo Shi, Heng Zhang, Xianghui Cao
Furthermore, by means of the labeled multi-Bernoulli (LMB) filter with the proposed augmented LRFSs, the group structure is iteratively propagated and updated during the tracking process, which achieves the simultaneously estimation of the kinetic states, track label, and the corresponding group information of multiple group targets, and further improves the GTT tracking performance.
1 code implementation • 7 Mar 2024 • Tao Zhou, Wenhan Luo, Qi Ye, Zhiguo Shi, Jiming Chen
Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images.
no code implementations • 10 Nov 2023 • Yuhao Chen, Yuxuan Yan, Qianqian Yang, Yuanchao Shu, Shibo He, Zhiguo Shi, Jiming Chen
Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training.
no code implementations • 8 Aug 2023 • Yuhao Chen, Qianqian Yang, Zhiguo Shi, Jiming Chen
In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency.
no code implementations • 2 Aug 2023 • Xingjian Wang, Li Chai, Jiming Chen, Zhiguo Shi
Multispectral pedestrian detection achieves better visibility in challenging conditions and thus has a broad application in various tasks, for which both the accuracy and computational cost are of paramount importance.
no code implementations • 23 Jun 2023 • Tianxiao Han, Kaiyi Chi, Qianqian Yang, Zhiguo Shi
As three-dimensional (3D) data acquisition devices become increasingly prevalent, the demand for 3D point cloud transmission is growing.
no code implementations • ICCV 2023 • Tao Zhou, Qi Ye, Wenhan Luo, Kaihao Zhang, Zhiguo Shi, Jiming Chen
Multi-object tracking (MOT) aims to build moving trajectories for number-agnostic objects.
no code implementations • 18 Nov 2022 • Tianxiao Han, Jiancheng Tang, Qianqian Yang, Yiping Duan, Zhaoyang Zhang, Zhiguo Shi
Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years.
no code implementations • 1 Nov 2022 • Yanyan Huang, Yong Wang, Kun Shi, Chaojie Gu, Yu Fu, Cheng Zhuo, Zhiguo Shi
Gait recognition is widely used in diversified practical applications.
no code implementations • 8 Sep 2022 • Zongyu Zhang, Zhiguo Shi, Yujie Gu
By contrast, the existing global tight Ziv-Zakai bound (ZZB) is appropriate for evaluating the single source estimation only.
1 code implementation • 27 May 2022 • Qiyuan Wang, Qianqian Yang, Shibo He, Zhiguo Shi, Jiming Chen
In an asynchronous federated learning framework, the server updates the global model once it receives an update from a client instead of waiting for all the updates to arrive as in the synchronous setting.
no code implementations • 25 May 2022 • Tianxiao Han, Qianqian Yang, Zhiguo Shi, Shibo He, Zhaoyang Zhang
Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years.
no code implementations • 31 Mar 2022 • Guangyang Zeng, Biqiang Mu, Jiming Chen, Zhiguo Shi, Junfeng Wu
In terms of whether the variance of measurement noises is known or not, we propose the Bias-Eli estimator (which involves solving a generalized trust region subproblem) and the Noise-Est estimator (which is obtained by solving a convex problem), respectively.
no code implementations • 7 Feb 2022 • Tianxiao Han, Qianqian Yang, Zhiguo Shi, Shibo He, Zhaoyang Zhang
We also propose a two-stage training scheme, which speeds up the training of the proposed DL model.
no code implementations • 6 Oct 2021 • Yuhao Chen, Qianqian Yang, Shibo He, Zhiguo Shi, Jiming Chen
Our numerical results demonstrate that FTPipeHD is 6. 8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one.
no code implementations • 7 Nov 2017 • Jiajun Zhang, Jinkun Tao, Jiangtao Huangfu, Zhiguo Shi
In this paper, a Doppler Radar based hand gesture recognition system using convolutional neural networks is proposed.
no code implementations • 6 Nov 2017 • Jiajun Zhang, Zhiguo Shi
Traditional vision-based hand gesture recognition systems is limited under dark circumstances.
BIG-bench Machine Learning Generative Adversarial Network +2