Search Results for author: Honggang Zhang

Found 64 papers, 9 papers with code

Self-Critical Alternate Learning based Semantic Broadcast Communication

no code implementations3 Dec 2023 Zhilin Lu, Rongpeng Li, Ming Lei, Chan Wang, Zhifeng Zhao, Honggang Zhang

In particular, to enable stable optimization via a nondifferentiable semantic metric, we regard sentence similarity as a reward and formulate this learning process as an RL problem.

Reinforcement Learning (RL) Semantic Similarity +3

Wired Perspectives: Multi-View Wire Art Embraces Generative AI

no code implementations26 Nov 2023 Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song

Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists.

Knowledge Distillation

Sketch-based Video Object Segmentation: Benchmark and Analysis

no code implementations13 Nov 2023 Ruolin Yang, Da Li, Conghui Hu, Timothy Hospedales, Honggang Zhang, Yi-Zhe Song

Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask.

Object Segmentation +3

Imitation Learning based Alternative Multi-Agent Proximal Policy Optimization for Well-Formed Swarm-Oriented Pursuit Avoidance

no code implementations6 Nov 2023 Sizhao Li, Yuming Xiang, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

Multi-Robot System (MRS) has garnered widespread research interest and fostered tremendous interesting applications, especially in cooperative control fields.

Imitation Learning

Alternate Learning based Sparse Semantic Communications for Visual Transmission

no code implementations31 Jul 2023 Siyu Tong, Xiaoxue Yu, Rongpeng Li, Kun Lu, Zhifeng Zhao, Honggang Zhang

Semantic communication (SemCom) demonstrates strong superiority over conventional bit-level accurate transmission, by only attempting to recover the essential semantic information of data.

Quantization

Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception

1 code implementation31 Jul 2023 Yuntao Liu, Qian Huang, Rongpeng Li, Xianfu Chen, Zhifeng Zhao, Shuyuan Zhao, Yongdong Zhu, Honggang Zhang

Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents.

Decentralized Adaptive Formation via Consensus-Oriented Multi-Agent Communication

no code implementations23 Jul 2023 Yuming Xiang, Sizhao Li, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

Adaptive multi-agent formation control, which requires the formation to flexibly adjust along with the quantity variations of agents in a decentralized manner, belongs to one of the most challenging issues in multi-agent systems, especially under communication-limited constraints.

Multi-agent Reinforcement Learning

NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services

no code implementations12 Jul 2023 Yuxuan Chen, Rongpeng Li, Zhifeng Zhao, Chenghui Peng, Jianjun Wu, Ekram Hossain, Honggang Zhang

Towards personalized generative services, a collaborative cloud-edge methodology is promising, as it facilitates the effective orchestration of heterogeneous distributed communication and computing resources.

Knowledge Enhanced Semantic Communication Receiver

no code implementations13 Feb 2023 Bingyan Wang, Rongpeng Li, Jianhang Zhu, Zhifeng Zhao, Honggang Zhang

In recent years, with the rapid development of deep learning and natural language processing technologies, semantic communication has become a topic of great interest in the field of communication.

Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection

no code implementations CVPR 2023 Xiaolin Song, Binghui Chen, Pengyu Li, Jun-Yan He, Biao Wang, Yifeng Geng, Xuansong Xie, Honggang Zhang

End-to-end pedestrian detection focuses on training a pedestrian detection model via discarding the Non-Maximum Suppression (NMS) post-processing.

Pedestrian Detection

Semantics-Empowered Communication: A Tutorial-cum-Survey

no code implementations16 Dec 2022 Zhilin Lu, Rongpeng Li, Kun Lu, Xianfu Chen, Ekram Hossain, Zhifeng Zhao, Honggang Zhang

Along with the springing up of the semantics-empowered communication (SemCom) research, it is now witnessing an unprecedentedly growing interest towards a wide range of aspects (e. g., theories, applications, metrics and implementations) in both academia and industry.

3D Reconstruction of Multiple Objects by mmWave Radar on UAV

no code implementations3 Nov 2022 Yue Sun, Zhuoming Huang, Honggang Zhang, Xiaohui Liang

The radar data is sent to a deep neural network model, which outputs the point cloud reconstruction of the multiple objects in the space.

3D Object Reconstruction Point cloud reconstruction

Age of Semantics in Cooperative Communications: To Expedite Simulation Towards Real via Offline Reinforcement Learning

no code implementations19 Sep 2022 Xianfu Chen, Zhifeng Zhao, Shiwen Mao, Celimuge Wu, Honggang Zhang, Mehdi Bennis

We then put forward a novel offline DAC scheme, which estimates the optimal control policy from a previously collected dataset without any further interactions with the system.

Reinforcement Learning (RL)

Learning Audio-Visual embedding for Person Verification in the Wild

no code implementations9 Sep 2022 Peiwen Sun, Shanshan Zhang, Zishan Liu, Yougen Yuan, Taotao Zhang, Honggang Zhang, Pengfei Hu

It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification.

Face Verification

AoI-based Temporal Attention Graph Neural Network for Popularity Prediction and Content Caching

no code implementations18 Aug 2022 Jianhang Zhu, Rongpeng Li, Guoru Ding, Chan Wang, Jianjun Wu, Zhifeng Zhao, Honggang Zhang

In this paper, to maximize the cache hit rate, we leverage an effective dynamic graph neural network (DGNN) to jointly learn the structural and temporal patterns embedded in the bipartite graph.

Contrastive Monotonic Pixel-Level Modulation

1 code implementation23 Jul 2022 Kun Lu, Rongpeng Li, Honggang Zhang

Continuous one-to-many mapping is a less investigated yet important task in both low-level visions and neural image translation.

Translation

R2P: A Deep Learning Model from mmWave Radar to Point Cloud

no code implementations21 Jul 2022 Yue Sun, Honggang Zhang, Zhuoming Huang, Benyuan Liu

Recent research has shown the effectiveness of mmWave radar sensing for object detection in low visibility environments, which makes it an ideal technique in autonomous navigation systems.

3D Reconstruction Autonomous Navigation +3

Adaptive Bit Rate Control in Semantic Communication with Incremental Knowledge-based HARQ

no code implementations13 Mar 2022 Qingyang Zhou, Rongpeng Li, Zhifeng Zhao, Yong Xiao, Honggang Zhang

Semantic communication has witnessed a great progress with the development of natural language processing (NLP) and deep learning (DL).

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

no code implementations30 Jan 2022 Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL).

Decision Making Federated Learning +2

RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training

no code implementations18 Jan 2022 Luya Wang, Feng Liang, Yangguang Li, Honggang Zhang, Wanli Ouyang, Jing Shao

Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability.

Contrastive Learning Representation Learning

Finding Badly Drawn Bunnies

1 code implementation CVPR 2022 Lan Yang, Kaiyue Pang, Honggang Zhang, Yi-Zhe Song

Our key discovery lies in exploiting the magnitude (L2 norm) of a sketch feature as a quantitative quality metric.

Rethinking Modern Communication from Semantic Coding to Semantic Communication

no code implementations16 Oct 2021 Kun Lu, Qingyang Zhou, Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Jianjun Wu, Honggang Zhang

Modern communications are usually designed to pursue a higher bit-level precision and fewer bits while transmitting a message.

Reinforcement Learning (RL)

DeepPoint: A Deep Learning Model for 3D Reconstruction in Point Clouds via mmWave Radar

no code implementations19 Sep 2021 Yue Sun, Honggang Zhang, Zhuoming Huang, Benyuan Liu

Built on our recent proposed 3DRIMR (3D Reconstruction and Imaging via mmWave Radar), we introduce in this paper DeepPoint, a deep learning model that generates 3D objects in point cloud format that significantly outperforms the original 3DRIMR design.

3D Reconstruction Autonomous Navigation +4

Reinforcement Learning-powered Semantic Communication via Semantic Similarity

1 code implementation27 Aug 2021 Kun Lu, Rongpeng Li, Xianfu Chen, Zhifeng Zhao, Honggang Zhang

We introduce a new semantic communication mechanism - SemanticRL, whose key idea is to preserve the semantic information instead of strictly securing the bit-level precision.

reinforcement-learning Reinforcement Learning (RL) +2

Semantic Communication with Adaptive Universal Transformer

no code implementations20 Aug 2021 Qingyang Zhou, Rongpeng Li, Zhifeng Zhao, Chenghui Peng, Honggang Zhang

With the development of deep learning (DL), natural language processing (NLP) makes it possible for us to analyze and understand a large amount of language texts.

Sentence

3DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learning

no code implementations5 Aug 2021 Yue Sun, Zhuoming Huang, Honggang Zhang, Zhi Cao, Deqiang Xu

In this paper we propose 3D Reconstruction and Imaging via mmWave Radar (3DRIMR), a deep learning based architecture that reconstructs 3D shape of an object in dense detailed point cloud format, based on sparse raw mmWave radar intensity data.

3D Reconstruction

The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication

no code implementations24 Mar 2021 Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

The paper considers independent reinforcement learning (IRL) for multi-agent collaborative decision-making in the paradigm of federated learning (FL).

Decision Making Federated Learning +3

SketchAA: Abstract Representation for Abstract Sketches

no code implementations ICCV 2021 Lan Yang, Kaiyue Pang, Honggang Zhang, Yi-Zhe Song

The superiority of explicitly abstracting sketch representation is empirically validated on a number of sketch analysis tasks, including sketch recognition, fine-grained sketch-based image retrieval, and generative sketch healing.

Retrieval Sketch-Based Image Retrieval +1

Deep Sketch-Based Modeling: Tips and Tricks

1 code implementation12 Nov 2020 Yue Zhong, Yulia Gryaditskaya, Honggang Zhang, Yi-Zhe Song

Deep image-based modeling received lots of attention in recent years, yet the parallel problem of sketch-based modeling has only been briefly studied, often as a potential application.

Learning to Prune in Training via Dynamic Channel Propagation

1 code implementation3 Jul 2020 Shibo Shen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang, Yugeng Zhou

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the neural networks during the training period.

Adaptive convolutional neural networks for k-space data interpolation in fast magnetic resonance imaging

no code implementations2 Jun 2020 Tianming Du, Honggang Zhang, Yuemeng Li, Hee Kwon Song, Yong Fan

Deep learning in k-space has demonstrated great potential for image reconstruction from undersampled k-space data in fast magnetic resonance imaging (MRI).

Image Reconstruction

Pseudo-Labeling for Small Lesion Detection on Diabetic Retinopathy Images

no code implementations26 Mar 2020 Qilei Chen, Ping Liu, Jing Ni, Yu Cao, Benyuan Liu, Honggang Zhang

The first one is that our dataset is not fully labeled, i. e., only a subset of all lesion instances are marked.

Lesion Detection object-detection +1

Convolutional Subspace Clustering Network with Block Diagonal Prior

no code implementations IEEE Access 2019 Junjian Zhang, Chun-Guang Li, Tianming Du, Honggang Zhang, Jun Guo

Standard methods of subspace clustering are based on self-expressiveness in the original data space, which states that a data point in a subspace can be expressed as a linear combination of other points.

Clustering

Stigmergic Independent Reinforcement Learning for Multi-Agent Collaboration

no code implementations28 Nov 2019 Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

With the rapid evolution of wireless mobile devices, there emerges an increased need to design effective collaboration mechanisms between intelligent agents, so as to gradually approach the final collective objective through continuously learning from the environment based on their individual observations.

reinforcement-learning Reinforcement Learning (RL)

A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing

no code implementations26 Aug 2019 Zhi Cao, Honggang Zhang, Yu Cao, Benyuan Liu

We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network.

Edge-computing reinforcement-learning +2

Age of Information-Aware Radio Resource Management in Vehicular Networks: A Proactive Deep Reinforcement Learning Perspective

no code implementations6 Aug 2019 Xianfu Chen, Celimuge Wu, Tao Chen, Honggang Zhang, Zhi Liu, Yan Zhang, Mehdi Bennis

In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network.

Decision Making Management +1

Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing

no code implementations10 Jun 2019 Chen Qi, Yuxiu Hua, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

Furthermore, as DPGD only works in continuous action space, we embed a k-nearest neighbor algorithm into DQL to quickly find a valid action in the discrete space nearest to the DPGD output.

Management Q-Learning +2

GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing

no code implementations10 May 2019 Yuxiu Hua, Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Honggang Zhang

Moreover, we further develop Dueling GAN-DDQN, which uses a specially designed dueling generator, to learn the action-value distribution by estimating the state-value distribution and the action advantage function.

Distributional Reinforcement Learning Generative Adversarial Network +3

Self-Supervised Convolutional Subspace Clustering Network

no code implementations CVPR 2019 Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin

However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces.

Clustering Image Clustering

Internet of Intelligence: The Collective Advantage for Advancing Communications and Intelligence

no code implementations26 Apr 2019 Rongpeng Li, Zhifeng Zhao, Xing Xu, Fei Ni, Honggang Zhang

Afterwards, we highlight the potential huge impact of CI on both communications and intelligence.

Test

Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group

no code implementations1 Mar 2019 Anna Dai, Zhifeng Zhao, Honggang Zhang, Rongpeng Li, Yugeng Zhou

Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action.

Decision Making Test

Brain-Inspired Stigmergy Learning

no code implementations20 Nov 2018 Xing Hsu, Zhifeng Zhao, Rongpeng Li, Honggang Zhang

Stigmergy has proved its great superiority in terms of distributed control, robustness and adaptability, thus being regarded as an ideal solution for large-scale swarm control problems.

Deep Learning with Long Short-Term Memory for Time Series Prediction

no code implementations24 Oct 2018 Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, Honggang Zhang

Time series prediction can be generalized as a process that extracts useful information from historical records and then determines future values.

Test Time Series +1

Deep Attentive Tracking via Reciprocative Learning

no code implementations NeurIPS 2018 Shi Pu, Yibing Song, Chao Ma, Honggang Zhang, Ming-Hsuan Yang

Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data.

Visual Tracking

AI-based Two-Stage Intrusion Detection for Software Defined IoT Networks

no code implementations7 Jun 2018 Jiaqi Li, Zhifeng Zhao, Rongpeng Li, Honggang Zhang

Software Defined Internet of Things (SD-IoT) Networks profits from centralized management and interactive resource sharing which enhances the efficiency and scalability of IoT applications.

Intrusion Detection Management +1

Deep Reinforcement Learning for Resource Management in Network Slicing

no code implementations17 May 2018 Rongpeng Li, Zhifeng Zhao, Qi Sun, Chi-Lin I, Chenyang Yang, Xianfu Chen, MinJian Zhao, Honggang Zhang

Network slicing is born as an emerging business to operators, by allowing them to sell the customized slices to various tenants at different prices.

Management reinforcement-learning +1

Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning

no code implementations16 May 2018 Xianfu Chen, Honggang Zhang, Celimuge Wu, Shiwen Mao, Yusheng Ji, Mehdi Bennis

To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services.

Edge-computing reinforcement-learning +1

Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification

no code implementations CVPR 2018 Jianlou Si, Honggang Zhang, Chun-Guang Li, Jason Kuen, Xiangfei Kong, Alex C. Kot, Gang Wang

Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space.

Person Re-Identification

Traffic Prediction Based on Random Connectivity in Deep Learning with Long Short-Term Memory

no code implementations8 Nov 2017 Yuxiu Hua, Zhifeng Zhao, Rongpeng Li, Xianfu Chen, Zhiming Liu, Honggang Zhang

So, the RCLSTM, with certain intrinsic sparsity, have many neural connections absent (distinguished from the full connectivity) and which leads to the reduction of the parameters to be trained and the computational cost.

Traffic Prediction

Residual Attention Network for Image Classification

20 code implementations CVPR 2017 Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang

In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion.

General Classification Image Classification +1

The Learning and Prediction of Application-level Traffic Data in Cellular Networks

no code implementations15 Jun 2016 Rongpeng Li, Zhifeng Zhao, Jianchao Zheng, Chengli Mei, Yueming Cai, Honggang Zhang

Afterwards, with the aid of the traffic "big data", we make a comprehensive study over the modeling and prediction framework of cellular network traffic.

Dictionary Learning Traffic Prediction

Deep Region and Multi-Label Learning for Facial Action Unit Detection

2 code implementations CVPR 2016 Kaili Zhao, Wen-Sheng Chu, Honggang Zhang

Region learning (RL) and multi-label learning (ML) have recently attracted increasing attentions in the field of facial Action Unit (AU) detection.

Action Unit Detection Facial Action Unit Detection +2

Learning Semi-Supervised Representation Towards a Unified Optimization Framework for Semi-Supervised Learning

no code implementations ICCV 2015 Chun-Guang Li, Zhouchen Lin, Honggang Zhang, Jun Guo

State of the art approaches for Semi-Supervised Learning (SSL) usually follow a two-stage framework -- constructing an affinity matrix from the data and then propagating the partial labels on this affinity matrix to infer those unknown labels.

Making Better Use of Edges via Perceptual Grouping

no code implementations CVPR 2015 Yonggang Qi, Yi-Zhe Song, Tao Xiang, Honggang Zhang, Timothy Hospedales, Yi Li, Jun Guo

We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks.

Learning-To-Rank Retrieval +1

Adaptive Learning of Region-based pLSA Model for Total Scene Annotation

no code implementations21 Nov 2013 Yuzhu Zhou, Le Li, Honggang Zhang

In this paper, we present a region-based pLSA model to accomplish the task of total scene annotation.

TAG

TACT: A Transfer Actor-Critic Learning Framework for Energy Saving in Cellular Radio Access Networks

no code implementations28 Nov 2012 Rongpeng Li, Zhifeng Zhao, Xianfu Chen, Jacques Palicot, Honggang Zhang

Recent works have validated the possibility of improving energy efficiency in radio access networks (RANs), achieved by dynamically turning on/off some base stations (BSs).

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.