1 code implementation • 29 Mar 2024 • Shunpu Tang, Qianqian Yang, Deniz Gündüz, Zhaoyang Zhang
In this paper, we explore an evolving semantic communication system for image transmission, referred to as ESemCom, with the capability to continuously enhance transmission efficiency.
no code implementations • 28 Mar 2024 • Zirui Chen, Zhaoyang Zhang, Zhaohui Yang, Chongwen Huang, Merouane Debbah
How to reduce the pilot overhead required for channel estimation?
1 code implementation • 27 Mar 2024 • Run Shao, Zhaoyang Zhang, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li
Compared to Patch Embed, which requires more than one hundred tokens for one image, HOOK requires only 6 and 8 tokens for sparse and dense tasks, respectively, resulting in efficiency improvements of 1. 5 to 2. 8 times.
no code implementations • 16 Feb 2024 • Richeng Jin, Yujie Gu, Kai Yue, Xiaofan He, Zhaoyang Zhang, Huaiyu Dai
In this paper, we propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously.
no code implementations • 7 Jan 2024 • Zirui Chen, Zhaoyang Zhang, Zhaohui Yang, Lei Liu
For such a channel mapping task, inspired by the intrinsic coupling across the space and frequency domains, this letter proposes to use interleaved learning with partial antenna and subcarrier characteristics to represent the whole MIMO-OFDM channel.
no code implementations • 1 Jan 2024 • Yulin Shao, Chenghong Bian, Li Yang, Qianqian Yang, Zhaoyang Zhang, Deniz Gunduz
Acquisition and processing of point clouds (PCs) is a crucial enabler for many emerging applications reliant on 3D spatial data, such as robot navigation, autonomous vehicles, and augmented reality.
1 code implementation • 20 Dec 2023 • Zhaoyang Zhang, Wenqi Shao, Yixiao Ge, Xiaogang Wang, Jinwei Gu, Ping Luo
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens.
no code implementations • 12 Dec 2023 • Chen Zhu, Zhouxiang Zhao, Zejing Shan, Lijie Yang, Sijie Ji, Zhaohui Yang, Zhaoyang Zhang
To improve the target detection performance under complex real-world scenarios, this paper proposes an intelligent integrated optical camera and millimeter-wave (mmWave) radar system.
1 code implementation • 16 Oct 2023 • Yitong Jiang, Zhaoyang Zhang, Tianfan Xue, Jinwei Gu
To this end, we propose an all-in-one image restoration framework with latent diffusion (AutoDIR), which can automatically detect and address multiple unknown degradations.
no code implementations • 25 Sep 2023 • Yihan Cang, Ming Chen, Zhaohui Yang, Yuntao Hu, Yinlu Wang, Chongwen Huang, Zhaoyang Zhang
To solve this problem, an online low-complexity algorithm is proposed.
no code implementations • 21 Sep 2023 • Yihan Cang, Ming Chen, Zhaohui Yang, Yuntao Hu, Yinlu Wang, Zhaoyang Zhang, Kai-Kit Wong
Moreover, the closed-form optimal solution of the semantic extraction factor is derived.
no code implementations • 16 Sep 2023 • Zhouxiang Zhao, Zhaohui Yang, Ye Hu, Licheng Lin, Zhaoyang Zhang
In this paper, the problem of semantic information extraction for resource constrained text data transmission is studied.
no code implementations • 6 Sep 2023 • Dezhi Wang, Chongwen Huang, Jiguang He, Xiaoming Chen, Wei Wang, Zhaoyang Zhang, Zhu Han, Mérouane Debbah
In this paper, we consider the environment sensing problem in the large-scale mobile crowd ISCC systems and propose an efficient waveform precoding design algorithm based on the mean field game~(MFG).
2 code implementations • 25 Aug 2023 • Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, Ping Luo
LWC modulates the extreme values of weights by optimizing the clipping threshold.
2 code implementations • 28 Jun 2023 • Zhaoyang Zhang, Zhen Ren, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li
Based on this, we propose contrastive learning with Gradient guided Sampling Strategy (GraSS) for RSI semantic segmentation.
no code implementations • 5 Jun 2023 • Weixuan Chen, Yuhao Chen, Qianqian Yang, Chongwen Huang, Qian Wang, Zhaoyang Zhang
Adaptive rate control for deep joint source and channel coding (JSCC) is considered as an effective approach to transmit sufficient information in scenarios with limited communication resources.
no code implementations • 4 Jun 2023 • Kaiyi Chi, Yingzhi Huang, Qianqian Yang, Zhaohui Yang, Zhaoyang Zhang
Precoding design for the downlink of multiuser multiple-input multiple-output (MU-MIMO) systems is a fundamental problem.
1 code implementation • 22 May 2023 • Zhuojun Tian, Zhaoyang Zhang, Zhaohui Yang, Richeng Jin, Huaiyu Dai
In conventional distributed learning over a network, multiple agents collaboratively build a common machine learning model.
no code implementations • 12 May 2023 • Senthil Kumar Jagatheesaperumal, Zhaohui Yang, Qianqian Yang, Chongwen Huang, Wei Xu, Mohammad Shikh-Bahaei, Zhaoyang Zhang
To facilitate the deployment of digital twins in Metaverse, the paradigm with semantic awareness has been proposed as a means for enabling accurate and task-oriented information extraction with inherent intelligence.
1 code implementation • 11 May 2023 • Zhaoyang Zhang, Yantao Shen, Kunyu Shi, Zhaowei Cai, Jun Fang, Siqi Deng, Hao Yang, Davide Modolo, Zhuowen Tu, Stefano Soatto
We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer.
no code implementations • 14 Apr 2023 • Ezgi C. Eren, Zhaoyang Zhang, Jonas Rauch, Ravi Kumar, Royce Kallesen
We develop a methodology to generate bid prices using historical booking data only.
no code implementations • 9 Apr 2023 • Zhuoran Xiao, Zhaoyang Zhang, Zirui Chen, Zhaohui Yang, Chongwen Huang, Xiaoming Chen
Then, we design a novel physics-inspired spatial channel gradient network (SCGnet), which represents the derivative process of channel varying as a special neural network and can obtain the gradients at any relative displacement needed for the ODE solving.
1 code implementation • CVPR 2023 • Zhaoyang Zhang, Yitong Jiang, Wenqi Shao, Xiaogang Wang, Ping Luo, Kaimo Lin, Jinwei Gu
Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness.
no code implementations • 9 Mar 2023 • Fenghao Zhu, Bohao Wang, Zhaohui Yang, Chongwen Huang, Zhaoyang Zhang, George C. Alexandropoulos, Chau Yuen, Merouane Debbah
Beamforming with large-scale antenna arrays has been widely used in recent years, which is acknowledged as an important part in 5G and incoming 6G.
no code implementations • 19 Feb 2023 • Richeng Jin, Xiaofan He, Caijun Zhong, Zhaoyang Zhang, Tony Quek, Huaiyu Dai
Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks.
no code implementations • NeurIPS 2023 • Richeng Jin, Zhonggen Su, Caijun Zhong, Zhaoyang Zhang, Tony Quek, Huaiyu Dai
We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability.
no code implementations • 3 Jan 2023 • Yahao Ding, Zhaohui Yang, Quoc-Viet Pham, Zhaoyang Zhang, Mohammad Shikh-Bahaei
In this survey, we first introduce several popular DL algorithms such as federated learning (FL), multi-agent Reinforcement Learning (MARL), distributed inference, and split learning, and present a comprehensive overview of their applications for UAV swarms, such as trajectory design, power control, wireless resource allocation, user assignment, perception, and satellite communications.
no code implementations • 5 Dec 2022 • Yourui Huangfu, Jian Wang, Shengchen Dai, Rong Li, Jun Wang, Chongwen Huang, Zhaoyang Zhang
The statistical data hinder the trained AI models from further fine-tuning for a specific scenario, and ray-tracing data with limited environments lower down the generalization capability of the trained AI models.
no code implementations • 2 Dec 2022 • Tierui Gong, Panagiotis Gavriilidis, Ran Ji, Chongwen Huang, George C. Alexandropoulos, Li Wei, Zhaoyang Zhang, Mérouane Debbah, H. Vincent Poor, Chau Yuen
In this survey, we present a comprehensive overview of the latest advances in the HMIMO communications paradigm, with a special focus on their physical aspects, their theoretical foundations, as well as the enabling technologies for HMIMO systems.
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.
2 code implementations • 15 Nov 2022 • Zhaoyang Zhang, Xuying Wang, Xiaoming Mei, Chao Tao, Haifeng Li
This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.
no code implementations • 2 Nov 2022 • Senthil Kumar Jagatheesaperumal, Quoc-Viet Pham, Rukhsana Ruby, Zhaohui Yang, Chunmei Xu, Zhaoyang Zhang
Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 31 Oct 2022 • Jingyu Li, Wei Liu, Zhaoyang Zhang, Jiong Wang, Tan Lee
Experimental results on VoxCeleb show that weight quantization is effective for compressing SV models.
no code implementations • 8 Oct 2022 • Yuzhi Yang, Zhaoyang Zhang, Zhaohui Yang
The precoding and combining matrices are trainable parameters in such a system, whereas the MIMO channel is implicit.
no code implementations • 7 Oct 2022 • Yuzhi Yang, Zhaoyang Zhang, Yuqing Tian, Zhaohui Yang, Chongwen Huang, Caijun Zhong, Kai-Kit Wong
In such a split ML system, the precoding and combining matrices are regarded as trainable parameters, while MIMO channel matrix is regarded as unknown (implicit) parameters.
no code implementations • 18 Sep 2022 • Minghui Wu, Zhen Gao, Yang Huang, Zhenyu Xiao, Derrick Wing Kwan Ng, Zhaoyang Zhang
Then, to acquire accurate CSI at the BS for the investigated RSMA precoding scheme to achieve higher spectral efficiency, we propose a CSI acquisition network (CAN) with low pilot and feedback signaling overhead, where the downlink pilot transmission, CSI feedback at the user equipments (UEs), and CSI reconstruction at the BS are modeled as an end-to-end neural network based on Transformer.
no code implementations • 8 Jul 2022 • Zhuoran Xiao, Zhaoyang Zhang, Zirui Chen, Zhaohui Yang, Richeng Jin
Through exploring the intrinsic correlation among a set of historical CSI instances randomly obtained in a certain communication environment, channel prediction can significantly increase CSI accuracy and save signaling overhead.
1 code implementation • 7 Jul 2022 • Wenqi Shao, Xun Zhao, Yixiao Ge, Zhaoyang Zhang, Lei Yang, Xiaogang Wang, Ying Shan, Ping Luo
It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive.
Ranked #2 on Transferability on classification benchmark
no code implementations • 2 Jul 2022 • Xin Tong, Zhaoyang Zhang, Yihan Zhang, Zhaohui Yang, Chongwen Huang, Kai-Kit Wong, Merouane Debbah
In this paper, we consider the problem of sensing the environment within a wireless cellular framework.
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 • 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 • 31 Dec 2021 • Lei Liu, Shunqi Huang, Yuzhi Yang, Zhaoyang Zhang, Brian M. Kurkoski
Given an arbitrary MAMP, we can construct an SS-MAMP by damping, which not only ensures the convergence of the state evolution, but also preserves the orthogonality, i. e., its dynamics can be correctly described by state evolution.
1 code implementation • ICLR 2022 • Wenqi Shao, Yixiao Ge, Zhaoyang Zhang, Xuyuan Xu, Xiaogang Wang, Ying Shan, Ping Luo
It is difficult for Transformers to capture inductive bias such as the positional context in an image with LN.
no code implementations • 5 Dec 2021 • Zhuoran Xiao, Zhaoyang Zhang, Chongwen Huang, Xiaoming Chen, Caijun Zhong, Mérouane Debbah
Specifically, we first use a forward deep neural network to infer the positions of all possible images of the source reflected by the surrounding scatterers within that environment, and then use the well-known Gaussian Radial Basis Function network (GRBF) to approximate the amplitudes of all possible propagation paths.
no code implementations • 16 Nov 2021 • Jiancheng Tang, Qianqian Yang, Zhaoyang Zhang
In this paper, we investigate the blind channel estimation problem for MIMO systems under Rayleigh fading channel.
no code implementations • 16 Nov 2021 • Yuqing Tian, Zhaoyang Zhang, Zhaohui Yang, Qianqian Yang
In this paper, a joint model split and neural architecture search (JMSNAS) framework is proposed to automatically generate and deploy a DNN model over a mobile edge network.
1 code implementation • 5 Oct 2021 • Yuzhi Yang, Zhaoyang Zhang, Qianqian Yang
{ Numerical results show that the proposed FL framework significantly reduces the communication cost compared to the conventional neural networks with typical real-valued parameters, and the performance loss incurred by the binarization can be further compensated by a hybrid method.
no code implementations • 6 Sep 2021 • Xin Tong, Zhaoyang Zhang, Jue Wang, Chongwen Huang, Merouane Debbah
As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing.
no code implementations • 13 May 2021 • Wenqi Shao, Hang Yu, Zhaoyang Zhang, Hang Xu, Zhenguo Li, Ping Luo
To address this problem, we develop a probability-based pruning algorithm, called batch whitening channel pruning (BWCP), which can stochastically discard unimportant channels by modeling the probability of a channel being activated.
1 code implementation • 15 Feb 2021 • Chaofan Tao, Rui Lin, Quan Chen, Zhaoyang Zhang, Ping Luo, Ngai Wong
Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.
no code implementations • 22 Jan 2021 • Chongwen Huang, Zhaohui Yang, George C. Alexandropoulos, Kai Xiong, Li Wei, Chau Yuen, Zhaoyang Zhang, Merouane Debbah
We investigate the joint design of digital beamforming matrix at the BS and analog beamforming matrices at the RISs, by leveraging the recent advances in deep reinforcement learning (DRL) to combat the propagation loss.
1 code implementation • ICCV 2021 • Zhaoyang Zhang, Yitong Jiang, Jun Jiang, Xiaogang Wang, Ping Luo, Jinwei Gu
STAR is a general architecture that can be easily adapted to different image enhancement tasks.
no code implementations • 29 Sep 2020 • Zhuojun Tian, Zhaoyang Zhang, Jue Wang, Xiaoming Chen, Wei Wang, Huaiyu Dai
In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system.
no code implementations • 20 Sep 2020 • Chongwen Huang, Zhaohui Yang, George C. Alexandropoulos, Kai Xiong, Li Wei, Chau Yuen, Zhaoyang Zhang
Wireless communication in the TeraHertz band (0. 1--10 THz) is envisioned as one of the key enabling technologies for the future six generation (6G) wireless communication systems.
no code implementations • 4 Aug 2020 • Li Wei, Chongwen Huang, George C. Alexandropoulos, Chau Yuen, Zhaoyang Zhang, Mérouane Debbah
We also discuss the downlink achievable sum rate computation with estimated channels and different precoding schemes for the base station.
1 code implementation • 21 Apr 2020 • Wenjie Li, Zhaoyang Zhang, Xinjiang Wang, Ping Luo
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
no code implementations • ICCV 2019 • Zhaoyang Zhang, Jingyu Li, Wenqi Shao, Zhanglin Peng, Ruimao Zhang, Xiaogang Wang, Ping Luo
ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers.
no code implementations • 15 Aug 2018 • Zhaoyang Zhang, Zhanghui Kuang, Ping Luo, Litong Feng, Wei zhang
Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.
no code implementations • 10 May 2018 • Xiaoyu Yue, Zhanghui Kuang, Zhaoyang Zhang, Zhenfang Chen, Pan He, Yu Qiao, Wei zhang
Deep CNNs have achieved great success in text detection.
1 code implementation • 1 Nov 2017 • Wei Lyu, Zhaoyang Zhang, Chunxu Jiao, Kangjian Qin, Huazi Zhang
With the demand of high data rate and low latency in fifth generation (5G), deep neural network decoder (NND) has become a promising candidate due to its capability of one-shot decoding and parallel computing.