no code implementations • 8 May 2024 • Pengyu Zhang, Yingjie Liu, Yingbo Zhou, Xiao Du, Xian Wei, Ting Wang, Mingsong Chen
Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.
no code implementations • 26 Feb 2024 • Pengyu Zhang, Yingbo Zhou, Ming Hu, Junxian Feng, Jiawen Weng, Mingsong Chen
Federated Instruction Tuning (FIT) has shown the ability to achieve collaborative model instruction tuning among massive data owners without sharing private data.
1 code implementation • 30 Jan 2024 • Rui Xiao, Lu Han, Xiaoying Zhou, Jiong Wang, Na Zong, Pengyu Zhang
In online learning platforms, particularly in rapidly growing computer programming courses, addressing the thousands of students' learning queries requires considerable human cost.
no code implementations • 15 Dec 2023 • Xiao Du, Yutong Ye, Pengyu Zhang, Yaning Yang, Mingsong Chen, Ting Wang
To this end, in this paper, we propose a novel MARL algorithm named Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning (SCIC), which incorporates a novel Intrinsic reward mechanism based on a new cooperation criterion measured by situation-dependent causal influence among agents.
no code implementations • 23 Nov 2023 • Ruixuan Liu, Ming Hu, Zeke Xia, Jun Xia, Pengyu Zhang, Yihao Huang, Yang Liu, Mingsong Chen
On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning.
no code implementations • 27 Jul 2023 • Yingbo Zhou, Zhihao Yue, Yutong Ye, Pengyu Zhang, Xian Wei, Mingsong Chen
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity.
no code implementations • 28 Jan 2023 • Pengyu Zhang, Yingbo Zhou, Ming Hu, Xin Fu, Xian Wei, Mingsong Chen
Based on the concept of Continual Learning (CL), we prove that CyclicFL approximates existing centralized pre-training methods in terms of classification and prediction performance.
no code implementations • 1 Nov 2022 • Bo Liang, Purui Wang, Renjie Zhao, Heyu Guo, Pengyu Zhang, Junchen Guo, Shunmin Zhu, Hongqiang Harry Liu, Xinyu Zhang, Chenren Xu
RFID localization is considered the key enabler of automating the process of inventory tracking and management for high-performance logistic network.
no code implementations • 10 Jul 2022 • Jiawen Zhu, Xin Chen, Pengyu Zhang, Xinying Wang, Dong Wang, Wenda Zhao, Huchuan Lu
Trackers tend to lose the target object due to the limited search region or be interfered with by distractors due to the excessive search region.
1 code implementation • CVPR 2022 • Pengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu, Xiang Ruan
With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information.
Ranked #4 on Rgb-T Tracking on GTOT
2 code implementations • 8 Dec 2020 • Pengyu Zhang, Dong Wang, Huchuan Lu
Visual object tracking, as a fundamental task in computer vision, has drawn much attention in recent years.
no code implementations • 4 Jul 2020 • Pengyu Zhang, Jie Zhao, Dong Wang, Huchuan Lu, Xiaoyun Yang
In this study, we propose a novel RGB-T tracking framework by jointly modeling both appearance and motion cues.
Ranked #6 on Rgb-T Tracking on GTOT
no code implementations • 26 Nov 2017 • Donghan Yu, Yong Li, Fengli Xu, Pengyu Zhang, Vassilis Kostakos
In this paper we present the first population-level, city-scale analysis of application usage on smartphones.
no code implementations • 21 Feb 2017 • Fengli Xu, Zhen Tu, Yong Li, Pengyu Zhang, Xiao-Ming Fu, Depeng Jin
By conducting experiments on two real-world datasets collected from both mobile application and cellular network, we reveal that the attack system is able to recover users' trajectories with accuracy about 73%~91% at the scale of tens of thousands to hundreds of thousands users, which indicates severe privacy leakage in such datasets.
Computers and Society Cryptography and Security