Search Results for author: Shuguang Cui

Found 137 papers, 38 papers with code

Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

1 code implementation NAACL 2022 Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.

Machine Translation Style Transfer +2

Leveraging A Variety of Anchors in Cellular Network for Ubiquitous Sensing

no code implementations26 Mar 2024 Liang Liu, Shuowen Zhang, Shuguang Cui

A key challenge of 6G-oriented ISAC lies in how to perform ubiquitous sensing based on the communication signals and devices.

Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

1 code implementation18 Mar 2024 Yuqi Zhang, GuanYing Chen, Jiaxing Chen, Shuguang Cui

We then introduce a novel cross-view instance label grouping strategy based on the 3D scene representation to mitigate the multi-view inconsistency problem in the 2D instance labels.

Instance Segmentation Novel View Synthesis +2

Generating, Reconstructing, and Representing Discrete and Continuous Data: Generalized Diffusion with Learnable Encoding-Decoding

no code implementations29 Feb 2024 Guangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu, Liping Tang, Yuan Gao, Zhen Li, Shuguang Cui, Julian McAuley, Eric P. Xing, Zichao Yang, Zhiting Hu

The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images.

Denoising

Fast and Accurate Cooperative Radio Map Estimation Enabled by GAN

no code implementations5 Feb 2024 Zezhong Zhang, Guangxu Zhu, Junting Chen, Shuguang Cui

In the 6G era, real-time radio resource monitoring and management are urged to support diverse wireless-empowered applications.

Generative Adversarial Network Management

Large Language Model Adaptation for Networking

no code implementations4 Feb 2024 Duo Wu, Xianda Wang, Yaqi Qiao, Zhi Wang, Junchen Jiang, Shuguang Cui, Fangxin Wang

In this paper, we present NetLLM, the first LLM adaptation framework that efficiently adapts LLMs to solve networking problems.

Answer Generation Language Modelling +3

Scalable Federated Unlearning via Isolated and Coded Sharding

no code implementations29 Jan 2024 Yijing Lin, Zhipeng Gao, Hongyang Du, Dusit Niyato, Gui Gui, Shuguang Cui, Jinke Ren

Federated unlearning has emerged as a promising paradigm to erase the client-level data effect without affecting the performance of collaborative learning models.

Codebook-enabled Generative End-to-end Semantic Communication Powered by Transformer

no code implementations22 Jan 2024 PeiGen Ye, Yaping Sun, Shumin Yao, Hao Chen, Xiaodong Xu, Shuguang Cui

Codebook-based generative semantic communication attracts increasing attention, since only indices are required to be transmitted when the codebook is shared between transmitter and receiver.

Image Generation

Integrated Sensing, Communication, and Powering (ISCAP): Towards Multi-functional 6G Wireless Networks

no code implementations7 Jan 2024 Yilong Chen, Zixiang Ren, Jie Xu, Yong Zeng, Derrick Wing Kwan Ng, Shuguang Cui

Specifically, a multi-functional base station (BS) can enable multi-functional transmission, by exploiting the same radio signals to perform target/environment sensing, wireless communication, and wireless power transfer (WPT), simultaneously.

Management

MOC-RVQ: Multilevel Codebook-assisted Digital Generative Semantic Communication

no code implementations2 Jan 2024 Yingbin Zhou, Yaping Sun, GuanYing Chen, Xiaodong Xu, Hao Chen, Binhong Huang, Shuguang Cui, Ping Zhang

Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face a challenge with conflicting requirements between codebook design and digital constellation modulation.

Quantization

RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation

no code implementations19 Dec 2023 Haiming Zhang, Xu Yan, Dongfeng Bai, Jiantao Gao, Pan Wang, Bingbing Liu, Shuguang Cui, Zhen Li

3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images.

Knowledge Distillation

GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance

no code implementations12 Dec 2023 Haiming Zhang, Zhihao Yuan, Chaoda Zheng, Xu Yan, Baoyuan Wang, Guanbin Li, Song Wu, Shuguang Cui, Zhen Li

Our proposed GSmoothFace model mainly consists of the Audio to Expression Prediction (A2EP) module and the Target Adaptive Face Translation (TAFT) module.

Face Model Talking Face Generation

Learning for Semantic Knowledge Base-Guided Online Feature Transmission in Dynamic Channels

no code implementations30 Nov 2023 Xiangyu Gao, Yaping Sun, Dongyu Wei, Xiaodong Xu, Hao Chen, Hao Yin, Shuguang Cui

In this context, we address the problem of efficient remote object recognition by optimizing feature transmission between mobile devices and edge servers.

Autonomous Vehicles Decision Making +2

Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding

no code implementations26 Nov 2023 Zhihao Yuan, Jinke Ren, Chun-Mei Feng, Hengshuang Zhao, Shuguang Cui, Zhen Li

Building on this, we design a visual program that consists of three types of modules, i. e., view-independent, view-dependent, and functional modules.

Object Visual Grounding

Knowledge Base Enabled Semantic Communication: A Generative Perspective

no code implementations21 Nov 2023 Jinke Ren, Zezhong Zhang, Jie Xu, GuanYing Chen, Yaping Sun, Ping Zhang, Shuguang Cui

Semantic communication is widely touted as a key technology for propelling the sixth-generation (6G) wireless networks.

Generative AI for Integrated Sensing and Communication: Insights from the Physical Layer Perspective

no code implementations2 Oct 2023 Jiacheng Wang, Hongyang Du, Dusit Niyato, Jiawen Kang, Shuguang Cui, Xuemin Shen, Ping Zhang

In this article, we investigate applications of GAI in the physical layer and analyze its support for integrated sensing and communications (ISAC) systems.

Efficient View Synthesis with Neural Radiance Distribution Field

no code implementations ICCV 2023 Yushuang Wu, Xiao Li, Jinglu Wang, Xiaoguang Han, Shuguang Cui, Yan Lu

Specifically, we use a small network similar to NeRF while preserving the rendering speed with a single network forwarding per pixel as in NeLF.

ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration

no code implementations19 Aug 2023 Duo Wu, Dayou Zhang, Miao Zhang, Ruoyu Zhang, Fangxin Wang, Shuguang Cui

The high-accuracy and resource-intensive deep neural networks (DNNs) have been widely adopted by live video analytics (VA), where camera videos are streamed over the network to resource-rich edge/cloud servers for DNN inference.

Imitation Learning

LATR: 3D Lane Detection from Monocular Images with Transformer

1 code implementation ICCV 2023 Yueru Luo, Chaoda Zheng, Xu Yan, Tang Kun, Chao Zheng, Shuguang Cui, Zhen Li

On the one hand, each query is generated based on 2D lane-aware features and adopts a hybrid embedding to enhance lane information.

3D Lane Detection Autonomous Driving

WeakPolyp: You Only Look Bounding Box for Polyp Segmentation

1 code implementation20 Jul 2023 Jun Wei, Yiwen Hu, Shuguang Cui, S. Kevin Zhou, Zhen Li

In contrast, polyp bounding box annotations are much cheaper and more accessible.

Over-the-Air Computation in OFDM Systems with Imperfect Channel State Information

no code implementations7 Jul 2023 Yilong Chen, Huijun Xing, Jie Xu, Lexi Xu, Shuguang Cui

In particular, we consider two scenarios with best-effort and error-constrained computation tasks, with the objectives of minimizing the average computation mean squared error (MSE) and the computation outage probability over the multiple subcarriers, respectively.

Universal Semi-supervised Model Adaptation via Collaborative Consistency Training

no code implementations7 Jul 2023 Zizheng Yan, Yushuang Wu, Yipeng Qin, Xiaoguang Han, Shuguang Cui, Guanbin Li

In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i. e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain.

Domain Adaptation

AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets

no code implementations16 Jun 2023 Yu Lu, Junwei Bao, Zichen Ma, Xiaoguang Han, Youzheng Wu, Shuguang Cui, Xiaodong He

High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design.

Knowledge Graphs Recommendation Systems

YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection

no code implementations6 Jun 2023 Yuncheng Jiang, Zixun Zhang, Ruimao Zhang, Guanbin Li, Shuguang Cui, Zhen Li

YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations.

Contrastive Learning

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning

no code implementations5 Jun 2023 Yao Tang, Guangxu Zhu, Wei Xu, Man Hon Cheung, Tat-Ming Lok, Shuguang Cui

Unmanned Aerial Vehicle (UAV)-mounted edge devices are particularly advantageous for FEEL due to their flexibility and mobility in efficient data collection.

Position Privacy Preserving

Heterogeneous Value Alignment Evaluation for Large Language Models

2 code implementations26 May 2023 Zhaowei Zhang, Ceyao Zhang, Nian Liu, Siyuan Qi, Ziqi Rong, Song-Chun Zhu, Shuguang Cui, Yaodong Yang

We conduct evaluations with new auto-metric \textit{value rationality} to represent the ability of LLMs to align with specific values.

Attribute

Hierarchical Weight Averaging for Deep Neural Networks

no code implementations23 Apr 2023 Xiaozhe Gu, Zixun Zhang, Yuncheng Jiang, Tao Luo, Ruimao Zhang, Shuguang Cui, Zhen Li

Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs).

Crossword: A Semantic Approach to Data Compression via Masking

no code implementations3 Apr 2023 Mingxiao Li, Rui Jin, Liyao Xiang, Kaiming Shen, Shuguang Cui

The traditional methods for data compression are typically based on the symbol-level statistics, with the information source modeled as a long sequence of i. i. d.

Data Compression

An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

1 code implementation21 Mar 2023 Chaoda Zheng, Xu Yan, Haiming Zhang, Baoyuan Wang, Shenghui Cheng, Shuguang Cui, Zhen Li

Due to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training.

3D Single Object Tracking Autonomous Driving +3

Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Features

1 code implementation6 Mar 2023 Yuqi Zhang, GuanYing Chen, Shuguang Cui

Based on this hybrid representation, we propose a fast optimization NeRF variant, called GP-NeRF, that achieves better rendering results while maintaining a compact model size.

HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling

1 code implementation CVPR 2023 Yujian Zheng, Zirong Jin, Moran Li, Haibin Huang, Chongyang Ma, Shuguang Cui, Xiaoguang Han

We firmly think an intermediate representation is essential, but we argue that orientation map using the dominant filtering-based methods is sensitive to uncertain noise and far from a competent representation.

Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors

no code implementations ICCV 2023 Zhangyang Xiong, Di Kang, Derong Jin, Weikai Chen, Linchao Bao, Shuguang Cui, Xiaoguang Han

Specifically, we bridge the latent space of Get3DHuman with that of StyleGAN-Human via a specially-designed prior network, where the input latent code is mapped to the shape and texture feature volumes spanned by the pixel-aligned 3D reconstructor.

Adaptive Context Selection for Polyp Segmentation

1 code implementation12 Jan 2023 Ruifei Zhang, Guanbin Li, Zhen Li, Shuguang Cui, Dahong Qian, Yizhou Yu

To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM).

Segmentation

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

1 code implementation3 Jan 2023 Xu Yan, Chaoda Zheng, Ying Xue, Zhen Li, Shuguang Cui, Dengxin Dai

In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions.

Autonomous Driving Benchmarking +3

BEV@DC: Bird's-Eye View Assisted Training for Depth Completion

no code implementations CVPR 2023 Wending Zhou, Xu Yan, Yinghong Liao, Yuankai Lin, Jin Huang, Gangming Zhao, Shuguang Cui, Zhen Li

In practice, the proposed BEV@DC model comprehensively takes advantage of LiDARs with rich geometric details in training, employing an enhanced depth completion manner in inference, which takes only images (RGB and depth) as input.

Autonomous Driving Depth Completion

Output-Dependent Gaussian Process State-Space Model

1 code implementation15 Dec 2022 Zhidi Lin, Lei Cheng, Feng Yin, Lexi Xu, Shuguang Cui

Gaussian process state-space model (GPSSM) is a fully probabilistic state-space model that has attracted much attention over the past decade.

MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction

1 code implementation9 Dec 2022 Shuliang Ning, Mengcheng Lan, Yanran Li, Chaofeng Chen, Qian Chen, Xunlai Chen, Xiaoguang Han, Shuguang Cui

The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner.

Video Prediction

BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations

1 code implementation7 Dec 2022 Jun Wei, Yiwen Hu, Guanbin Li, Shuguang Cui, S Kevin Zhou, Zhen Li

In practice, box annotations are applied to alleviate the over-fitting issue of previous polyp segmentation models, which generate fine-grained polyp area through the iterative boosted segmentation model.

Segmentation

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

no code implementations2 Dec 2022 Yinghong Liao, Wending Zhou, Xu Yan, Shuguang Cui, Yizhou Yu, Zhen Li

Moreover, to improve the 2D classifier in the target domain, we perform domain-invariant geometric adaptation from source to target and unify the 2D semantic and 3D geometric segmentation results in two domains.

Depth Estimation Depth Prediction +4

MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking

no code implementations10 Nov 2022 Haoning Zhang, Junwei Bao, Haipeng Sun, Youzheng Wu, Wenye Li, Shuguang Cui, Xiaodong He

Then, the noised previous state is used as the input to learn to predict the current state, improving the model's ability to update and correct slot values.

Dialogue State Tracking

MetaLoc: Learning to Learn Wireless Localization

no code implementations8 Nov 2022 Jun Gao, Dongze Wu, Feng Yin, Qinglei Kong, Lexi Xu, Shuguang Cui

The framework introduces two paradigms for the optimization of meta-parameters: a centralized paradigm that simplifies the process by sharing data from all historical environments, and a distributed paradigm that maintains data privacy by training meta-parameters for each specific environment separately.

Meta-Learning

CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking

no code implementations11 Oct 2022 Haoning Zhang, Junwei Bao, Haipeng Sun, Huaishao Luo, Wenye Li, Shuguang Cui

The unlabeled data of the DST task is incorporated into the self-training iterations, where the pseudo labels are predicted by a DST model trained on limited labeled data in advance.

Dialogue State Tracking Machine Reading Comprehension +2

Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

2 code implementations9 Oct 2022 Xu Yan, Heshen Zhan, Chaoda Zheng, Jiantao Gao, Ruimao Zhang, Shuguang Cui, Zhen Li

Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i. e., rendered or projected 2D images of the 3D object, to boost point cloud analysis.

3D Point Cloud Classification Knowledge Distillation +1

Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks

no code implementations21 Sep 2022 Sihua Wang, Mingzhe Chen, Christopher G. Brinton, Changchuan Yin, Walid Saad, Shuguang Cui

Compared to model-free RL, this model-based RL approach leverages the derived mathematical characterization of the FL training process to discover an effective device selection and quantization scheme without imposing additional device communication overhead.

Federated Learning Model-based Reinforcement Learning +2

Personalizing or Not: Dynamically Personalized Federated Learning with Incentives

no code implementations12 Aug 2022 Zichen Ma, Yu Lu, Wenye Li, Shuguang Cui

This dynamically personalized FL technique incentivizes clients to participate in personalizing local models while allowing the adoption of the global model when it performs better.

Personalized Federated Learning

Low-Latency Cooperative Spectrum Sensing via Truncated Vertical Federated Learning

no code implementations7 Aug 2022 Zezhong Zhang, Guangxu Zhu, Shuguang Cui

To accelerate the training process, we propose a truncated vertical federated learning (T-VFL) algorithm, where the training latency is highly reduced by integrating the standard VFL algorithm with a channel-aware user scheduling policy.

Scheduling Vertical Federated Learning

Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes

1 code implementation18 Jul 2022 Haolin Liu, Yujian Zheng, GuanYing Chen, Shuguang Cui, Xiaoguang Han

We present a new framework to reconstruct holistic 3D indoor scenes including both room background and indoor objects from single-view images.

Object Reconstruction Vocal Bursts Intensity Prediction

Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases

no code implementations5 Jul 2022 Zhihao Yuan, Xu Yan, Zhuo Li, Xuhao Li, Yao Guo, Shuguang Cui, Zhen Li

Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description.

Object Representation Learning +3

Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI

no code implementations3 Jul 2022 Dingzhu Wen, Peixi Liu, Guangxu Zhu, Yuanming Shi, Jie Xu, Yonina C. Eldar, Shuguang Cui

This paper studies a new multi-device edge artificial-intelligent (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) to enable low-latency intelligent services at the network edge.

Management Quantization

Networked Sensing in 6G Cellular Networks: Opportunities and Challenges

no code implementations1 Jun 2022 Liang Liu, Shuowen Zhang, Rui Du, Tong Xiao Han, Shuguang Cui

This article will discuss about the possibility of exploiting the future sixth-generation (6G) cellular network to realize ISAC.

Multi-level Consistency Learning for Semi-supervised Domain Adaptation

1 code implementation9 May 2022 Zizheng Yan, Yushuang Wu, Guanbin Li, Yipeng Qin, Xiaoguang Han, Shuguang Cui

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain.

Domain Adaptation Semi-supervised Domain Adaptation

DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation

no code implementations25 Apr 2022 Liangdong Qiu, Chongjie Ye, Pei Chen, Yunbi Liu, Xiaoguang Han, Shuguang Cui

Experimental results on $4, 773$ dental models have shown our DArch can accurately segment each tooth of a dental model, and its performance is superior to the state-of-the-art methods.

Instance Segmentation Segmentation +1

PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds

no code implementations22 Feb 2022 Yushuang Wu, Zizheng Yan, Shengcai Cai, Guanbin Li, Yizhou Yu, Xiaoguang Han, Shuguang Cui

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated.

Representation Learning Weakly supervised Semantic Segmentation +1

Vertical Federated Edge Learning with Distributed Integrated Sensing and Communication

no code implementations21 Jan 2022 Peixi Liu, Guangxu Zhu, Wei Jiang, Wu Luo, Jie Xu, Shuguang Cui

This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC).

DArch: Dental Arch Prior-Assisted 3D Tooth Instance Segmentation With Weak Annotations

no code implementations CVPR 2022 Liangdong Qiu, Chongjie Ye, Pei Chen, Yunbi Liu, Xiaoguang Han, Shuguang Cui

Experimental results on 4, 773 dental models have shown our DArch can accurately segment each tooth of a dental model, and its performance is superior to the state-of-the-art methods.

Instance Segmentation Segmentation +1

ETHSeg: An Amodel Instance Segmentation Network and a Real-World Dataset for X-Ray Waste Inspection

no code implementations CVPR 2022 Lingteng Qiu, Zhangyang Xiong, Xuhao Wang, Kenkun Liu, Yihan Li, GuanYing Chen, Xiaoguang Han, Shuguang Cui

Inspired by the fact that X-ray has a strong penetrating power to see through the bag and overlapping objects, we propose to perform waste inspection efficiently using X-ray images without the need to open the bag.

Instance Segmentation Segmentation +1

Federated Two-stage Learning with Sign-based Voting

no code implementations10 Dec 2021 Zichen Ma, Zihan Lu, Yu Lu, Wenye Li, JinFeng Yi, Shuguang Cui

In this paper, we design a federated two-stage learning framework that augments prototypical federated learning with a cut layer on devices and uses sign-based stochastic gradient descent with the majority vote method on model updates.

BIG-bench Machine Learning Federated Learning +2

Joint LED Selection and Precoding Optimization for Multiple-User Multiple-Cell VLC Systems

no code implementations29 Aug 2021 Yang Yang, Yujie Yang, Mingzhe Chen, Chunyan Feng, Hailun Xia, Shuguang Cui, H. Vincent Poor

First, a MU-MC-VLC system model is established, and then a sum-rate maximization problem under dimming level and illumination uniformity constraints is formulated.

Device-Free Sensing in OFDM Cellular Network

no code implementations20 Aug 2021 Qin Shi, Liang Liu, Shuowen Zhang, Shuguang Cui

A novel two-phase sensing framework is proposed to localize the passive targets that cannot transmit/receive reference signals to/from the base stations (BSs), where the ranges of the targets are estimated based on their reflected OFDM signals to the BSs in Phase I, and the location of each target is estimated based on its ranges to different BSs in Phase II.

Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

2 code implementations ICCV 2021 Chaoda Zheng, Xu Yan, Jiantao Gao, Weibing Zhao, Wei zhang, Zhen Li, Shuguang Cui

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.

3D Single Object Tracking Object +1

Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment

no code implementations5 Aug 2021 Qin Wang, Hui Che, Weizhen Ding, Li Xiang, Guanbin Li, Zhen Li, Shuguang Cui

Thus, we propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification (CPC) through directly using white-light (WL) colonoscopy images in the examination.

Contrastive Learning

Shallow Feature Matters for Weakly Supervised Object Localization

1 code implementation CVPR 2021 Jun Wei, Qin Wang, Zhen Li, Sheng Wang, S. Kevin Zhou, Shuguang Cui

In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.

Object Pseudo Label +1

Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling

no code implementations24 Jul 2021 Maojun Zhang, Guangxu Zhu, Shuai Wang, Jiamo Jiang, Caijun Zhong, Shuguang Cui

Building on the analytical result, an optimized probabilistic scheduling policy is derived in closed-form by solving the approximate communication time minimization problem.

Autonomous Driving Learning Theory +2

From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting

no code implementations21 Jul 2021 Mengcheng Lan, Shuliang Ning, Yanran Li, Qian Chen, Xunlai Chen, Xiaoguang Han, Shuguang Cui

Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces.

Video Prediction

Task-Aware Sampling Layer for Point-Wise Analysis

no code implementations9 Jul 2021 Yiqun Lin, Lichang Chen, Haibin Huang, Chongyang Ma, Xiaoguang Han, Shuguang Cui

Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds.

Keypoint Detection Point Cloud Completion +1

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

1 code implementation29 Jun 2021 Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.

Machine Translation Style Transfer +3

Towards Heterogeneous Clients with Elastic Federated Learning

no code implementations17 Jun 2021 Zichen Ma, Yu Lu, Zihan Lu, Wenye Li, JinFeng Yi, Shuguang Cui

Training in heterogeneous and potentially massive networks introduces bias into the system, which is originated from the non-IID data and the low participation rate in reality.

Federated Learning

RevCore: Review-augmented Conversational Recommendation

1 code implementation Findings (ACL) 2021 Yu Lu, Junwei Bao, Yan Song, Zichen Ma, Shuguang Cui, Youzheng Wu, Xiaodong He

Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items.

Response Generation

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

1 code implementation30 Apr 2021 Weibing Zhao, Xu Yan, Jiantao Gao, Ruimao Zhang, Jiayan Zhang, Zhen Li, Song Wu, Shuguang Cui

In this paper, we address a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarding points in a case-agnostic manner (i. e. without additional storage for point relationship)?

Distributed Reinforcement Learning for Age of Information Minimization in Real-Time IoT Systems

no code implementations4 Apr 2021 Sihua Wang, Mingzhe Chen, Zhaohui Yang, Changchuan Yin, Walid Saad, Shuguang Cui, H. Vincent Poor

In this paper, the problem of minimizing the weighted sum of age of information (AoI) and total energy consumption of Internet of Things (IoT) devices is studied.

reinforcement-learning Reinforcement Learning (RL) +1

Recent Advances in Data-Driven Wireless Communication Using Gaussian Processes: A Comprehensive Survey

no code implementations18 Mar 2021 Kai Chen, Qinglei Kong, Yijue Dai, Yue Xu, Feng Yin, Lexi Xu, Shuguang Cui

Empowered by big data and machine learning, next-generation data-driven communication systems will be intelligent with the characteristics of expressiveness, scalability, interpretability, and especially uncertainty modeling, which can confidently involve diversified latent demands and personalized services in the foreseeable future.

BIG-bench Machine Learning Gaussian Processes

Optimization of User Selection and Bandwidth Allocation for Federated Learning in VLC/RF Systems

no code implementations5 Mar 2021 Chuanhong Liu, Caili Guo, Yang Yang, Mingzhe Chen, H. Vincent Poor, Shuguang Cui

Then, the problem of user selection and bandwidth allocation is studied for FL implemented over a hybrid VLC/RF system aiming to optimize the FL performance.

Federated Learning

Meta-Reinforcement Learning for Reliable Communication in THz/VLC Wireless VR Networks

1 code implementation29 Jan 2021 Yining Wang, Mingzhe Chen, Zhaohui Yang, Walid Saad, Tao Luo, Shuguang Cui, H. Vincent Poor

The problem is formulated as an optimization problem whose goal is to maximize the reliability of the VR network by selecting the appropriate VAPs to be turned on and controlling the user association with SBSs.

Meta-Learning Meta Reinforcement Learning +2

A Comprehensive Survey on 6G Networks:Applications, Core Services, Enabling Technologies, and Future Challenges

no code implementations29 Jan 2021 Amin Shahraki, Mahmoud Abbasi, Md. Jalil Piran, Mingzhe Chen, Shuguang Cui

Cellular Internet of Things (IoT) is considered as de facto paradigm to improve the communication and computation systems.

Networking and Internet Architecture

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

2 code implementations7 Dec 2020 Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.

3D Semantic Scene Completion from a single RGB image 3D Semantic Segmentation +3

Distributed Multi-agent Meta Learning for Trajectory Design in Wireless Drone Networks

no code implementations6 Dec 2020 Ye Hu, Mingzhe Chen, Walid Saad, H. Vincent Poor, Shuguang Cui

Analytical results show that, the proposed VD-RL algorithm is guaranteed to converge to a local optimal solution of the non-convex optimization problem.

Meta-Learning Navigate

On the Adversarial Robustness of LASSO Based Feature Selection

no code implementations20 Oct 2020 Fuwei Li, Lifeng Lai, Shuguang Cui

We formulate the modification strategy of the adversary as a bi-level optimization problem.

Adversarial Robustness feature selection

A Machine Learning Approach for Task and Resource Allocation in Mobile Edge Computing Based Networks

no code implementations20 Jul 2020 Sihua Wang, Mingzhe Chen, Xuanlin Liu, Changchuan Yin, Shuguang Cui, H. Vincent Poor

Since the data size of each computational task is different, as the requested computational task varies, the BSs must adjust their resource (subcarrier and transmit power) and task allocation schemes to effectively serve the users.

BIG-bench Machine Learning Edge-computing +2

Delay Minimization for Federated Learning Over Wireless Communication Networks

no code implementations5 Jul 2020 Zhaohui Yang, Mingzhe Chen, Walid Saad, Choong Seon Hong, Mohammad Shikh-Bahaei, H. Vincent Poor, Shuguang Cui

In this paper, the problem of delay minimization for federated learning (FL) over wireless communication networks is investigated.

Federated Learning

From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

no code implementations1 Jul 2020 Songyang Zhang, Han Zhang, Shuguang Cui, Zhi Ding

Graph convolutional networks (GCN) have been recently utilized to extract the underlying structures of datasets with some labeled data and high-dimensional features.

Node Classification

UVeQFed: Universal Vector Quantization for Federated Learning

1 code implementation5 Jun 2020 Nir Shlezinger, Mingzhe Chen, Yonina C. Eldar, H. Vincent Poor, Shuguang Cui

We show that combining universal vector quantization methods with FL yields a decentralized training system in which the compression of the trained models induces only a minimum distortion.

Federated Learning Quantization

Wireless Communications for Collaborative Federated Learning

no code implementations3 Jun 2020 Mingzhe Chen, H. Vincent Poor, Walid Saad, Shuguang Cui

However, due to resource constraints and privacy challenges, edge IoT devices may not be able to transmit their collected data to a central controller for training machine learning models.

BIG-bench Machine Learning Federated Learning +2

Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks

no code implementations25 May 2020 Ye Hu, Mingzhe Chen, Walid Saad, H. Vincent Poor, Shuguang Cui

Meanwhile, the probability that the DBS serves over 50% of user requests increases about 27%, compared to the baseline policy gradient algorithm.

Meta-Learning Meta Reinforcement Learning +2

Energy-Efficient Wireless Communications with Distributed Reconfigurable Intelligent Surfaces

no code implementations1 May 2020 Zhaohui Yang, Mingzhe Chen, Walid Saad, Wei Xu, Mohammad Shikh-Bahaei, H. Vincent Poor, Shuguang Cui

In this network, multiple RISs are spatially distributed to serve wireless users and the energy efficiency of the network is maximized by dynamically controlling the on-off status of each RIS as well as optimizing the reflection coefficients matrix of the RISs.

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

2 code implementations ECCV 2020 Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han

High-fidelity clothing reconstruction is the key to achieving photorealism in a wide range of applications including human digitization, virtual try-on, etc.

Garment Reconstruction Virtual Try-on

Peeking into occluded joints: A novel framework for crowd pose estimation

1 code implementation ECCV 2020 Lingteng Qiu, Xuanye Zhang, Yan-ran Li, Guanbin Li, Xiao-Jun Wu, Zixiang Xiong, Xiaoguang Han, Shuguang Cui

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions.

Pose Estimation

Federated Learning for Task and Resource Allocation in Wireless High Altitude Balloon Networks

no code implementations19 Mar 2020 Sihua Wang, Mingzhe Chen, Changchuan Yin, Walid Saad, Choong Seon Hong, Shuguang Cui, H. Vincent Poor

This problem is posed as an optimization problem whose goal is to minimize the energy and time consumption for task computing and transmission by adjusting the user association, service sequence, and task allocation scheme.

Edge-computing Federated Learning

Scalable Learning Paradigms for Data-Driven Wireless Communication

no code implementations1 Mar 2020 Yue Xu, Feng Yin, Wenjun Xu, Chia-Han Lee, Jia-Ru Lin, Shuguang Cui

The marriage of wireless big data and machine learning techniques revolutionizes the wireless system by the data-driven philosophy.

Philosophy

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling

1 code implementation CVPR 2020 Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui

Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise.

3D Point Cloud Classification Semantic Segmentation

Optimal Feature Manipulation Attacks Against Linear Regression

no code implementations29 Feb 2020 Fuwei Li, Lifeng Lai, Shuguang Cui

In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points.

regression

Artificial Intelligence Aided Next-Generation Networks Relying on UAVs

no code implementations28 Jan 2020 Xiao Liu, Mingzhe Chen, Yuanwei Liu, Yue Chen, Shuguang Cui, Lajos Hanzo

Artificial intelligence (AI) assisted unmanned aerial vehicle (UAV) aided next-generation networking is proposed for dynamic environments.

Position

Convergence Time Optimization for Federated Learning over Wireless Networks

no code implementations22 Jan 2020 Mingzhe Chen, H. Vincent Poor, Walid Saad, Shuguang Cui

Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step.

Federated Learning

Point Cloud Segmentation based on Hypergraph Spectral Clustering

no code implementations21 Jan 2020 Songyang Zhang, Shuguang Cui, Zhi Ding

Hypergraph spectral analysis has emerged as an effective tool processing complex data structures in data analysis.

Clustering Point Cloud Segmentation +1

Hypergraph Spectral Analysis and Processing in 3D Point Cloud

no code implementations8 Jan 2020 Songyang Zhang, Shuguang Cui, Zhi Ding

Along with increasingly popular virtual reality applications, the three-dimensional (3D) point cloud has become a fundamental data structure to characterize 3D objects and surroundings.

Denoising

A Joint Learning and Communications Framework for Federated Learning over Wireless Networks

1 code implementation17 Sep 2019 Mingzhe Chen, Zhaohui Yang, Walid Saad, Changchuan Yin, H. Vincent Poor, Shuguang Cui

This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize an FL loss function that captures the performance of the FL algorithm.

Federated Learning

On the Adversarial Robustness of Subspace Learning

no code implementations17 Aug 2019 Fuwei Li, Lifeng Lai, Shuguang Cui

We first characterize the optimal rank-one attack strategy that maximizes the subspace distance between the subspace learned from the original data matrix and that learned from the modified data matrix.

Adversarial Robustness

Introducing Hypergraph Signal Processing: Theoretical Foundation and Practical Applications

no code implementations22 Jul 2019 Songyang Zhang, Zhi Ding, Shuguang Cui

Signal processing over graphs has recently attracted significant attentions for dealing with structured data.

Voting-Based Multi-Agent Reinforcement Learning for Intelligent IoT

no code implementations2 Jul 2019 Yue Xu, Zengde Deng, Mengdi Wang, Wenjun Xu, Anthony Man-Cho So, Shuguang Cui

The recent success of single-agent reinforcement learning (RL) in Internet of things (IoT) systems motivates the study of multi-agent reinforcement learning (MARL), which is more challenging but more useful in large-scale IoT.

Decision Making Multi-agent Reinforcement Learning +2

Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach

no code implementations3 Jun 2019 Yue Xu, Wenjun Xu, Zhi Wang, Jia-Ru Lin, Shuguang Cui

Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way.

reinforcement-learning Reinforcement Learning (RL)

Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image

no code implementations CVPR 2019 Xiaoguang Han, Zhaoxuan Zhang, Dong Du, Mingdai Yang, Jingming Yu, Pan Pan, Xin Yang, Ligang Liu, Zixiang Xiong, Shuguang Cui

Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud.

Wireless Traffic Prediction with Scalable Gaussian Process: Framework, Algorithms, and Verification

no code implementations13 Feb 2019 Yue Xu, Feng Yin, Wenjun Xu, Jia-Ru Lin, Shuguang Cui

First, to the best of our knowledge, this paper is the first to empower GP regression with the alternating direction method of multipliers (ADMM) for parallel hyper-parameter optimization in the training phase, where such a scalable training framework well balances the local estimation in baseband units (BBUs) and information consensus among BBUs in a principled way for large-scale executions.

regression Traffic Prediction

Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images

no code implementations18 Jan 2019 Zizheng Yan, Xiaoguang Han, Changmiao Wang, Yuda Qiu, Zixiang Xiong, Shuguang Cui

Due to high-resolution and small-size lesion regions, applying existing methods, such as U-Nets, to perform segmentation on fundus photography is very challenging.

Lesion Segmentation Segmentation

Multi-Antenna Channel Interpolation via Tucker Decomposed Extreme Learning Machine

no code implementations26 Dec 2018 Han Zhang, Bo Ai, Wenjun Xu, Li Xu, Shuguang Cui

Channel interpolation is an essential technique for providing high-accuracy estimation of the channel state information (CSI) for wireless systems design where the frequency-space structural correlations of multi-antenna channel are typically hidden in matrix or tensor forms.

A Two-Step Learning and Interpolation Method for Location-Based Channel Database

no code implementations4 Dec 2018 Ruichen Deng, Zhiyuan Jiang, Sheng Zhou, Shuguang Cui, Zhisheng Niu

Timely and accurate knowledge of channel state information (CSI) is necessary to support scheduling operations at both physical and network layers.

Scheduling

Fast Similarity Search via Optimal Sparse Lifting

no code implementations NeurIPS 2018 Wenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui

Similarity search is a fundamental problem in computing science with various applications and has attracted significant research attention, especially in large-scale search with high dimensions.

CaricatureShop: Personalized and Photorealistic Caricature Sketching

no code implementations24 Jul 2018 Xiaoguang Han, Kangcheng Hou, Dong Du, Yuda Qiu, Yizhou Yu, Kun Zhou, Shuguang Cui

To construct the mapping between 2D sketches and a vertex-wise scaling field, a novel deep learning architecture is developed.

Caricature Face Model

Detection of Cooperative Interactions in Logistic Regression Models

no code implementations12 Feb 2016 Easton Li Xu, Xiaoning Qian, Tie Liu, Shuguang Cui

For the case when the underlying interaction graph is known to be acyclic, it is shown that a simple algorithm that is based on a maximum-weight spanning tree with respect to the plug-in estimates of the influences not only has strong theoretical performance guarantees, but can also outperform generic feature selection algorithms for recovering the interaction graph from i. i. d.

feature selection regression

Cognitive Learning of Statistical Primary Patterns via Bayesian Network

no code implementations28 Sep 2014 Weijia Han, Huiyan Sang, Min Sheng, Jiandong Li, Shuguang Cui

How to learn such a BN structure is a long standing issue, not fully understood even in the statistical learning community.

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