Search Results for author: Jun Zhang

Found 143 papers, 35 papers with code

BMInf: An Efficient Toolkit for Big Model Inference and Tuning

no code implementations ACL 2022 Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie zhou, Jun Zhang, Jia Chao, Maosong Sun

In recent years, large-scale pre-trained language models (PLMs) containing billions of parameters have achieved promising results on various NLP tasks.

Quantization

KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals

no code implementations Findings (EMNLP) 2021 Jun Zhang, Yan Yang, Chencai Chen, Liang He, Zhou Yu

Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation.

Question Answering Recommendation Systems +1

Hybrid Far- and Near-Field Channel Estimation for THz Ultra-Massive MIMO via Fixed Point Networks

no code implementations10 May 2022 Wentao Yu, Yifei Shen, Hengtao He, Xianghao Yu, Jun Zhang, Khaled B. Letaief

We draw inspirations from fixed point theory to develop an efficient deep learning based channel estimator with adaptive complexity and linear convergence guarantee.

Pan-cancer computational histopathology reveals tumor mutational burden status through weakly-supervised deep learning

no code implementations7 Apr 2022 Siteng Chen, Jinxi Xiang, Xiyue Wang, Jun Zhang, Sen yang, Junzhou Huang, Wei Yang, Junhua Zheng, Xiao Han

In comparison with the state-of-the-art TMB prediction model from previous publications, our multiscale model achieved better performance over previously reported models.

whole slide images

Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack

no code implementations22 Mar 2022 Chi Liu, Huajie Chen, Tianqing Zhu, Jun Zhang, Wanlei Zhou

To evaluate the attack efficacy, we crafted heterogeneous security scenarios where the detectors were embedded with different levels of defense and the attackers' background knowledge of data varies.

Face Swapping

Graph Neural Networks for Wireless Communications: From Theory to Practice

1 code implementation21 Mar 2022 Yifei Shen, Jun Zhang, S. H. Song, Khaled B. Letaief

For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement.

Communication-Efficient Federated Distillation with Active Data Sampling

no code implementations14 Mar 2022 Lumin Liu, Jun Zhang, S. H. Song, Khaled B. Letaief

Federated Distillation (FD) is a recently proposed alternative to enable communication-efficient and robust FL, which achieves orders of magnitude reduction of the communication overhead compared with FedAvg and is flexible to handle heterogeneous models at the clients.

Federated Learning Privacy Preserving Deep Learning

AugHover-Net: Augmenting Hover-net for Nucleus Segmentation and Classification

no code implementations4 Mar 2022 Wenhua Zhang, Jun Zhang

Connective nuclei may look very different from each other while some of them share a similar shape with the epithelial ones.

Classification

The Gene of Scientific Success

no code implementations17 Feb 2022 Xiangjie Kong, Jun Zhang, Da Zhang, Yi Bu, Ying Ding, Feng Xia

Under this consideration, our paper presents and analyzes the causal factors that are crucial for scholars' academic success.

Stochastic Coded Federated Learning with Convergence and Privacy Guarantees

no code implementations25 Jan 2022 Yuchang Sun, Jiawei Shao, Songze Li, Yuyi Mao, Jun Zhang

Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework, where many clients collaboratively train a machine learning model by exchanging model updates with a parameter server instead of sharing their raw data.

Federated Learning

Data-Driven Deep Learning Based Hybrid Beamforming for Aerial Massive MIMO-OFDM Systems with Implicit CSI

no code implementations18 Jan 2022 Zhen Gao, Minghui Wu, Chun Hu, Feifei Gao, Guanghui Wen, Dezhi Zheng, Jun Zhang

To this end, by modeling the key transmission modules as an end-to-end (E2E) neural network, this paper proposes a data-driven deep learning (DL)-based unified hybrid beamforming framework for both the time division duplex (TDD) and frequency division duplex (FDD) systems with implicit channel state information (CSI).

Quantization Transfer Learning

A Critical Analysis of Image-based Camera Pose Estimation Techniques

no code implementations15 Jan 2022 Meng Xu, Youchen Wang, Bin Xu, Jun Zhang, Jian Ren, Stefan Poslad, Pengfei Xu

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR).

Autonomous Driving Camera Localization +2

Weighted Encoding Optimization for Dynamic Single-pixel Imaging and Sensing

no code implementations8 Jan 2022 Xinrui Zhan, Liheng Bian, Chunli Zhu, Jun Zhang

While the network is training at a high sampling rate, the modulation patterns and corresponding weights are updated iteratively, which produces optimal ranked encoding series when converged.

Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity

no code implementations20 Dec 2021 Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated learning.

Federated Learning

Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients

no code implementations9 Dec 2021 Yuchang Sun, Jiawei Shao, Yuyi Mao, Jun Zhang

Federated edge learning (FEEL) has drawn much attention as a privacy-preserving distributed learning framework for mobile edge networks.

Learn to Communicate with Neural Calibration: Scalability and Generalization

no code implementations1 Oct 2021 Yifan Ma, Yifei Shen, Xianghao Yu, Jun Zhang, S. H. Song, Khaled B. Letaief

Furthermore, such networks will vary dynamically in a significant way, which makes it intractable to develop comprehensive analytical models.

Federated Learning with GAN-based Data Synthesis for Non-IID Clients

no code implementations29 Sep 2021 Zijian Li, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

Specifically, each client pretrains a local generative adversarial network (GAN) to generate synthetic data, which are uploaded to the parameter server (PS) to construct a global shared synthetic dataset.

Federated Learning

Task-Oriented Communication for Multi-Device Cooperative Edge Inference

no code implementations1 Sep 2021 Jiawei Shao, Yuyi Mao, Jun Zhang

To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i. e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server.

Sk-Unet Model with Fourier Domain for Mitosis Detection

no code implementations1 Sep 2021 Sen yang, Feng Luo, Jun Zhang, Xiyue Wang

Mitotic count is the most important morphological feature of breast cancer grading.

Mitosis Detection

Communication-Computation Efficient Device-Edge Co-Inference via AutoML

no code implementations30 Aug 2021 Xinjie Zhang, Jiawei Shao, Yuyi Mao, Jun Zhang

Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligent mobile applications.

AutoML Image Classification

$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection

1 code implementation29 Aug 2021 Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang

For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.

Classification OOD Detection +2

Image-free single-pixel segmentation

no code implementations24 Aug 2021 Haiyan Liu, Liheng Bian, Jun Zhang

We envision that this image-free segmentation technique can be widely applied in various resource-limited platforms such as UAV and unmanned vehicle that require real-time sensing.

Semantic Segmentation

Semantic Reinforced Attention Learning for Visual Place Recognition

no code implementations19 Aug 2021 Guohao Peng, Yufeng Yue, Jun Zhang, Zhenyu Wu, Xiaoyu Tang, Danwei Wang

(2) By exploiting the interpretability of the local weighting scheme, a semantic constrained initialization is proposed so that the local attention can be reinforced by semantic priors.

Visual Place Recognition

How Powerful is Graph Convolution for Recommendation?

1 code implementation17 Aug 2021 Yifei Shen, Yongji Wu, Yao Zhang, Caihua Shan, Jun Zhang, Khaled B. Letaief, Dongsheng Li

In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing.

Collaborative Filtering

Neural Calibration for Scalable Beamforming in FDD Massive MIMO with Implicit Channel Estimation

no code implementations3 Aug 2021 Yifan Ma, Yifei Shen, Xianghao Yu, Jun Zhang, S. H. Song, Khaled B. Letaief

Channel estimation and beamforming play critical roles in frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems.

Primary-Auxiliary Model Scheduling Based Estimation of the Vertical Wheel Force in a Full Vehicle System

no code implementations24 Jul 2021 Xueke Zheng, Runze Cai, Shuixin Xiao, Yu Qiu, Jun Zhang, Mian Li

A real-world application to the estimation of the vertical wheel force in a full vehicle system are, respectively, conducted to demonstrate the effectiveness of the proposed method.

Deep Adaptive Arbitrary Polynomial Chaos Expansion: A Mini-data-driven Semi-supervised Method for Uncertainty Quantification

no code implementations22 Jul 2021 Wen Yao, Xiaohu Zheng, Jun Zhang, Ning Wang, Guijian Tang

Based on the adaptive aPC, a semi-supervised deep adaptive arbitrary polynomial chaos expansion (Deep aPCE) method is proposed to reduce the training data cost and improve the surrogate model accuracy.

Dimensionality Reduction

RBUE: A ReLU-Based Uncertainty Estimation Method of Deep Neural Networks

no code implementations15 Jul 2021 Yufeng Xia, Jun Zhang, Zhiqiang Gong, Tingsong Jiang, Wen Yao

Deep Ensemble is widely considered the state-of-the-art method which can estimate the uncertainty with higher quality, but it is very expensive to train and test.

Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-free Massive Random Access

no code implementations12 Jul 2021 Xinyu Bian, Yuyi Mao, Jun Zhang

In particular, the common sparsity pattern in the received pilot and data signal has been ignored in most existing studies, and auxiliary information of channel decoding has not been utilized for user activity detection.

Action Detection Activity Detection

IDRLnet: A Physics-Informed Neural Network Library

1 code implementation9 Jul 2021 Wei Peng, Jun Zhang, Weien Zhou, Xiaoyu Zhao, Wen Yao, Xiaoqian Chen

Physics Informed Neural Network (PINN) is a scientific computing framework used to solve both forward and inverse problems modeled by Partial Differential Equations (PDEs).

Physics-Informed Deep Reversible Regression Model for Temperature Field Reconstruction of Heat-Source Systems

1 code implementation22 Jun 2021 Zhiqiang Gong, Weien Zhou, Jun Zhang, Wei Peng, Wen Yao

To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly.

Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification

1 code implementation CVPR 2021 Jiaxing Chen, Xinyang Jiang, Fudong Wang, Jun Zhang, Feng Zheng, Xing Sun, Wei-Shi Zheng

In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.

3D Reconstruction Person Re-Identification

Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution

no code implementations13 Jun 2021 Huapeng Wu, Jie Gui, Jun Zhang, James T. Kwok, Zhihui Wei

Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost.

Image Super-Resolution

Feedback Pyramid Attention Networks for Single Image Super-Resolution

no code implementations13 Jun 2021 Huapeng Wu, Jie Gui, Jun Zhang, James T. Kwok, Zhihui Wei

Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement.

Image Super-Resolution

Invariant Information Bottleneck for Domain Generalization

no code implementations11 Jun 2021 Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.

Domain Generalization

Agile wide-field imaging with selective high resolution

no code implementations9 Jun 2021 Lintao Peng, Liheng Bian, Tiexin Liu, Jun Zhang

In this work, we report an agile wide-field imaging framework with selective high resolution that requires only two detectors.

A Comprehensive Survey and Taxonomy on Image Dehazing Based on Deep Learning

1 code implementation7 Jun 2021 Jie Gui, Xiaofeng Cong, Yuan Cao, Wenqi Ren, Jun Zhang, Jing Zhang, Jiuxin Cao, DaCheng Tao

With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed.

Image Dehazing

Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey

no code implementations13 May 2021 XiaoYu Zhang, Chao Chen, Yi Xie, Xiaofeng Chen, Jun Zhang, Yang Xiang

This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.

Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression

no code implementations26 Apr 2021 Zhefeng Qiao, Xianghao Yu, Jun Zhang, Khaled B. Letaief

Federated learning (FL) is a promising and powerful approach for training deep learning models without sharing the raw data of clients.

Federated Learning Low-rank compression

Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data

no code implementations26 Apr 2021 Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

Federated edge learning (FEEL) has emerged as an effective approach to reduce the large communication latency in Cloud-based machine learning solutions, while preserving data privacy.

Federated Learning

Joint Activity Detection and Data Decoding in Massive Random Access via a Turbo Receiver

no code implementations26 Apr 2021 Xinyu Bian, Yuyi Mao, Jun Zhang

In this paper, we propose a turbo receiver for joint activity detection and data decoding in grant-free massive random access, which iterates between a detector and a belief propagation (BP)-based channel decoder.

Action Detection Activity Detection

Affine-modeled video extraction from a single motion blurred image

no code implementations8 Apr 2021 Daoyu Li, Liheng Bian, Jun Zhang

Recovering these sharp video frames from a single blurred image is nontrivial, due to not only its strong ill-posedness, but also various types of complex motion in reality such as rotation and motion in depth.

Frame

Large-scale phase retrieval

no code implementations6 Apr 2021 Xuyang Chang, Liheng Bian, Jun Zhang

In computational phase imaging, phase retrieval (PR) is required to reconstruct both amplitude and phase in complex space from intensity-only measurements.

Decentralized Statistical Inference with Unrolled Graph Neural Networks

1 code implementation4 Apr 2021 He Wang, Yifei Shen, Ziyuan Wang, Dongsheng Li, Jun Zhang, Khaled B. Letaief, Jie Lu

In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.

HMM-Free Encoder Pre-Training for Streaming RNN Transducer

no code implementations2 Apr 2021 Lu Huang, Jingyu Sun, Yufeng Tang, JunFeng Hou, Jinkun Chen, Jun Zhang, Zejun Ma

This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model.

Frame Speech Recognition

Hierarchical Quantized Federated Learning: Convergence Analysis and System Design

no code implementations26 Mar 2021 Lumin Liu, Jun Zhang, Shenghui Song, Khaled B. Letaief

The high communication efficiency comes from frequent local aggregations at the edge servers and fewer aggregations at the cloud server, as well as weight quantization during model uploading.

Federated Learning Quantization

A Deep Neural Network Surrogate Modeling Benchmark for Temperature Field Prediction of Heat Source Layout

1 code implementation20 Mar 2021 Xianqi Chen, Xiaoyu Zhao, Zhiqiang Gong, Jun Zhang, Weien Zhou, Xiaoqian Chen, Wen Yao

Thermal issue is of great importance during layout design of heat source components in systems engineering, especially for high functional-density products.

Model Selection

Single-photon imaging over 200 km

no code implementations10 Mar 2021 Zheng-Ping Li, Jun-Tian Ye, Xin Huang, Peng-Yu Jiang, Yuan Cao, Yu Hong, Chao Yu, Jun Zhang, Qiang Zhang, Cheng-Zhi Peng, Feihu Xu, Jian-Wei Pan

Long-range active imaging has widespread applications in remote sensing and target recognition.

Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query

1 code implementation ICCV 2021 Guanyu Cai, Jun Zhang, Xinyang Jiang, Yifei Gong, Lianghua He, Fufu Yu, Pai Peng, Xiaowei Guo, Feiyue Huang, Xing Sun

However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.

Cross-Modal Retrieval Image Retrieval

Supporting More Active Users for Massive Access via Data-assisted Activity Detection

no code implementations17 Feb 2021 Xinyu Bian, Yuyi Mao, Jun Zhang

Massive machine-type communication (mMTC) has been regarded as one of the most important use scenarios in the fifth generation (5G) and beyond wireless networks, which demands scalable access for a large number of devices.

Action Detection Activity Detection

Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey

2 code implementations16 Feb 2021 Yuantian Miao, Chao Chen, Lei Pan, Qing-Long Han, Jun Zhang, Yang Xiang

Stealing attack against controlled information, along with the increasing number of information leakage incidents, has become an emerging cyber security threat in recent years.

Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach

1 code implementation8 Feb 2021 Jiawei Shao, Yuyi Mao, Jun Zhang

Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.

Informativeness

Attentional Pyramid Pooling of Salient Visual Residuals for Place Recognition

no code implementations ICCV 2021 Guohao Peng, Jun Zhang, Heshan Li, Danwei Wang

The core of visual place recognition (VPR) lies in how to identify task-relevant visual cues and embed them into discriminative representations.

Visual Place Recognition

Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales

no code implementations22 Dec 2020 Jun Zhang, Yaqiang Zhou, Yao-Kun Lei, Yi Isaac Yang, Yi Qin Gao

Deep learning is changing many areas in molecular physics, and it has shown great potential to deliver new solutions to challenging molecular modeling problems.

Representation Learning

Hawking radiation from nonrotating singularity-free black holes in conformal gravity

no code implementations2 Dec 2020 Jun Zhang, Yuan Sun

Besides, we investigate the dependence of the greybody factor and the sparsity of Hawking radiation on the conformal parameters.

General Relativity and Quantum Cosmology

Deep Reinforcement Learning of Transition States

no code implementations13 Nov 2020 Jun Zhang, Yao-Kun Lei, Zhen Zhang, Xu Han, Maodong Li, Lijiang Yang, Yi Isaac Yang, Yi Qin Gao

Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach (RL$^\ddag$) to automatically unravel chemical reaction mechanisms.

reinforcement-learning

Dynamic latency speech recognition with asynchronous revision

no code implementations3 Nov 2020 Mingkun Huang, Meng Cai, Jun Zhang, Yang Zhang, Yongbin You, Yi He, Zejun Ma

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models.

Speech Recognition

Improving RNN transducer with normalized jointer network

no code implementations3 Nov 2020 Mingkun Huang, Jun Zhang, Meng Cai, Yang Zhang, Jiali Yao, Yongbin You, Yi He, Zejun Ma

In this work, we analyze the cause of the huge gradient variance in RNN-T training and proposed a new \textit{normalized jointer network} to overcome it.

Automatic Speech Recognition

Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing

1 code implementation27 Oct 2020 Jiawei Shao, Haowei Zhang, Yuyi Mao, Jun Zhang

The recent advancements of three-dimensional (3D) data acquisition devices have spurred a new breed of applications that rely on point cloud data processing.

Distributed, Parallel, and Cluster Computing

DeFuzz: Deep Learning Guided Directed Fuzzing

no code implementations23 Oct 2020 Xiaogang Zhu, Shigang Liu, Xian Li, Sheng Wen, Jun Zhang, Camtepe Seyit, Yang Xiang

Fuzzing is one of the most effective technique to identify potential software vulnerabilities.

Vulnerability Detection

From em-Projections to Variational Auto-Encoder

no code implementations NeurIPS Workshop DL-IG 2020 Tian Han, Jun Zhang, Ying Nian Wu

This paper reviews the em-projections in information geometry and the recent understanding of variational auto-encoder, and explains that they share a common formulation as joint minimization of the Kullback-Leibler divergence between two manifolds of probability distributions, and the joint minimization can be implemented by alternating projections or alternating gradient descent.

Group-Buying Recommendation for Social E-Commerce

1 code implementation14 Oct 2020 Jun Zhang, Chen Gao, Depeng Jin, Yong Li

Group-buying recommendation for social e-commerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales.

Microscope Based HER2 Scoring System

no code implementations15 Sep 2020 Jun Zhang, Kuan Tian, Pei Dong, Haocheng Shen, Kezhou Yan, Jianhua Yao, Junzhou Huang, Xiao Han

Recently, artificial intelligence (AI) has been used in various disease diagnosis to improve diagnostic accuracy and reliability, but the interpretation of diagnosis results is still an open problem.

Flow Field Reconstructions with GANs based on Radial Basis Functions

no code implementations11 Aug 2020 Liwei Hu, Wenyong Wang, Yu Xiang, Jun Zhang

Motivated by the problems of existing approaches and inspired by the success of the generative adversarial networks (GANs) in the field of computer vision, we prove an optimal discriminator theorem that the optimal discriminator of a GAN is a radial basis function neural network (RBFNN) while dealing with nonlinear sparse FFD regression and generation.

Robust Ego and Object 6-DoF Motion Estimation and Tracking

2 code implementations28 Jul 2020 Jun Zhang, Mina Henein, Robert Mahony, Viorela Ila

The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task.

Autonomous Driving Motion Estimation +2

Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis

1 code implementation15 Jul 2020 Yifei Shen, Yuanming Shi, Jun Zhang, Khaled B. Letaief

In this paper, we propose to apply graph neural networks (GNNs) to solve large-scale radio resource management problems, supported by effective neural network architecture design and theoretical analysis.

Distributed Optimization

EPI-based Oriented Relation Networks for Light Field Depth Estimation

1 code implementation9 Jul 2020 Kunyuan Li, Jun Zhang, Rui Sun, Xu-Dong Zhang, Jun Gao

Based on the observation that an oriented line and its neighboring pixels in an EPI share a similar linear structure, we propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical EPIs.

Data Augmentation Depth Estimation

Communication-Computation Trade-Off in Resource-Constrained Edge Inference

1 code implementation3 Jun 2020 Jiawei Shao, Jun Zhang

The recent breakthrough in artificial intelligence (AI), especially deep neural networks (DNNs), has affected every branch of science and technology.

Edge-computing Model Compression

Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces

1 code implementation3 Jun 2020 Shicong Liu, Zhen Gao, Jun Zhang, Marco Di Renzo, Mohamed-Slim Alouini

Integrating large intelligent reflecting surfaces (IRS) into millimeter-wave (mmWave) massive multi-input-multi-ouput (MIMO) has been a promising approach for improved coverage and throughput.

Compressive Sensing Denoising

VDO-SLAM: A Visual Dynamic Object-aware SLAM System

1 code implementation22 May 2020 Jun Zhang, Mina Henein, Robert Mahony, Viorela Ila

Combining Simultaneous Localisation and Mapping (SLAM) estimation and dynamic scene modelling can highly benefit robot autonomy in dynamic environments.

Robotics

Cores in discrete exchange economies with complex endowments

no code implementations19 May 2020 Jun Zhang

The core is a traditional and useful solution concept in economic theory.

Efficient and fair trading algorithms in market design environments

no code implementations14 May 2020 Jingsheng Yu, Jun Zhang

We propose a new method to define trading algorithms in market design environments.

Fairness

Target-based Sentiment Annotation in Chinese Financial News

no code implementations LREC 2020 Chaofa Yuan, Yu-Han Liu, Rongdi Yin, Jun Zhang, Qinling Zhu, Ruibin Mao, Ruifeng Xu

Based on high quality annotation guideline and effective quality control strategy, a corpus with 8, 314 target-level sentiment annotation is constructed on 6, 336 paragraphs from Chinese financial news text.

Sentiment Analysis

The Design and Construction of a Chinese Sarcasm Dataset

no code implementations LREC 2020 Xiaochang Gong, Qin Zhao, Jun Zhang, Ruibin Mao, Ruifeng Xu

Thus, the detection and processing of sarcasm is important to social media analysis. However, most existing sarcasm dataset are in English and there is still a lack of authoritative Chinese sarcasm dataset.

Blind Data Detection in Massive MIMO via $\ell_3$-norm Maximization over the Stiefel Manifold

no code implementations26 Apr 2020 Ye Xue, Yifei Shen, Vincent Lau, Jun Zhang, Khaled B. Letaief

Specifically, we propose a novel $\ell_3$-norm-based formulation to recover the data without channel estimation.

A Perspective on Deep Learning for Molecular Modeling and Simulations

no code implementations25 Apr 2020 Jun Zhang, Yao-Kun Lei, Zhen Zhang, Junhan Chang, Maodong Li, Xu Han, Lijiang Yang, Yi Isaac Yang, Yi Qin Gao

Deep learning is transforming many areas in science, and it has great potential in modeling molecular systems.

Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

1 code implementation17 Apr 2020 Wei Peng, Weien Zhou, Jun Zhang, Wen Yao

Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical guarantee of corresponding error bounds.

Scene Text Recognition via Transformer

no code implementations18 Mar 2020 Xinjie Feng, Hongxun Yao, Yuankai Qi, Jun Zhang, Shengping Zhang

Different from previous transformer based models [56, 34], which just use the decoder of the transformer to decode the convolutional attention, the proposed method use a convolutional feature maps as word embedding input into transformer.

Scene Text Recognition

GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering

1 code implementation ECCV 2020 Chuang Niu, Jun Zhang, Ge Wang, Jimin Liang

To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping.

Image Clustering Representation Learning +1

Efficient reinforcement learning control for continuum robots based on Inexplicit Prior Knowledge

1 code implementation26 Feb 2020 Junjia Liu, Jiaying Shou, Zhuang Fu, Hangfei Zhou, Rongli Xie, Jun Zhang, Jian Fei, Yanna Zhao

Moreover, recent reinforcement learning methods are data-inefficient and can not be directly deployed to the robot without simulation.

reinforcement-learning Visual Tracking

How many infections of COVID-19 there will be in the "Diamond Princess"-Predicted by a virus transmission model based on the simulation of crowd flow

1 code implementation25 Feb 2020 Zhiming Fang, Zhongyi Huang, Xiaolian Li, Jun Zhang, Wei Lv, Lei Zhuang, Xingpeng Xu, Nan Huang

Objectives: Simulate the transmission process of COVID-19 in a cruise ship, and then to judge how many infections there will be in the 3711 people in the "Diamond Princess" and analyze measures that could have prevented mass transmission.

Physics and Society Computers and Society

Complete Dictionary Learning via $\ell_p$-norm Maximization

1 code implementation24 Feb 2020 Yifei Shen, Ye Xue, Jun Zhang, Khaled B. Letaief, Vincent Lau

Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics.

Dictionary Learning Representation Learning

Sparse Optimization for Green Edge AI Inference

no code implementations24 Feb 2020 Xiangyu Yang, Sheng Hua, Yuanming Shi, Hao Wang, Jun Zhang, Khaled B. Letaief

By exploiting the inherent connections between the set of task selection and group sparsity structural transmit beamforming vector, we reformulate the optimization as a group sparse beamforming problem.

Combinatorial Optimization Edge-computing

DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

no code implementations23 Feb 2020 Qingjian Lin, Weicheng Cai, Lin Yang, Jun-Jie Wang, Jun Zhang, Ming Li

Our diarization system includes multiple modules, namely voice activity detection (VAD), segmentation, speaker embedding extraction, similarity scoring, clustering, resegmentation and overlap detection.

Action Detection Activity Detection

Communication-Efficient Edge AI: Algorithms and Systems

no code implementations22 Feb 2020 Yuanming Shi, Kai Yang, Tao Jiang, Jun Zhang, Khaled B. Letaief

By pushing inference and training processes of AI models to edge nodes, edge AI has emerged as a promising alternative.

Drug Discovery Image Classification

Dynamic SLAM: The Need For Speed

1 code implementation20 Feb 2020 Mina Henein, Jun Zhang, Robert Mahony, Viorela Ila

In this paper, we propose a new feature-based, model-free, object-aware dynamic SLAM algorithm that exploits semantic segmentation to allow estimation of motion of rigid objects in a scene without the need to estimate the object poses or have any prior knowledge of their 3D models.

Robotics

Faster Activity and Data Detection in Massive Random Access: A Multi-armed Bandit Approach

no code implementations28 Jan 2020 Jialin Dong, Jun Zhang, Yuanming Shi, Jessie Hui Wang

In this paper, we develop multi-armed bandit approaches for more efficient detection via coordinate descent, which make a delicate trade-off between exploration and exploitation in coordinate selection.

Action Detection Activity Detection

Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar

no code implementations18 Nov 2019 Bin Li, Shuseng Wang, Jun Zhang, Xainbin Cao, Chenglin Zhao

Massive multiple-input multiple-output (MIMO) radar, enabled by millimeter-wave virtual MIMO techniques, provides great promises to the high-resolution automotive sensing and target detection in unmanned ground/aerial vehicles (UGA/UAV).

A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification

no code implementations4 Nov 2019 Shigang Liu, Jun Zhang, Yang Xiang, Wanlei Zhou, Dongxi Xiang

However, previous studies usually focused on different classifiers, and overlook the class imbalance problem in real-world biomedical datasets.

Drug Discovery General Classification

BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems

1 code implementation31 Oct 2019 Jiawei Shao, Jun Zhang

By exploiting the strong sparsity and the fault-tolerant property of the intermediate feature in a deep neural network (DNN), BottleNet++ achieves a much higher compression ratio than existing methods.

Edge-computing

Multi-grained Attention Networks for Single Image Super-Resolution

no code implementations26 Sep 2019 Huapeng Wu, Zhengxia Zou, Jie Gui, Wen-Jun Zeng, Jieping Ye, Jun Zhang, Hongyi Liu, Zhihui Wei

In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.

Feature Importance Image Super-Resolution

Non-imaging single-pixel sensing with optimized binary modulation

no code implementations25 Sep 2019 Hao Fu, Liheng Bian, Jun Zhang

The conventional high-level sensing techniques require high-fidelity images as input to extract target features, which are produced by either complex imaging hardware or high-complexity reconstruction algorithms.

General Classification Image Classification

Constrained Pseudo-market Equilibrium

no code implementations12 Sep 2019 Federico Echenique, Antonio Miralles, Jun Zhang

We propose a pseudo-market solution to resource allocation problems subject to constraints.

Restricted Linearized Augmented Lagrangian Method for Euler's Elastica Model

no code implementations5 Aug 2019 Yinghui Zhang, Xiaojuan Deng, Jun Zhang, Hongwei Li

In this paper, a simple cutting-off strategy is introduced into the augmented Lagrangian based algorithms for minimizing the Euler's elastica energy, which leads to easy parameter tuning and fast convergence.

A Graph Neural Network Approach for Scalable Wireless Power Control

2 code implementations19 Jul 2019 Yifei Shen, Yuanming Shi, Jun Zhang, Khaled B. Letaief

Specifically, a $K$-user interference channel is first modeled as a complete graph, where the quantitative information of wireless channels is incorporated as the features of the graph.

Light Field Saliency Detection with Deep Convolutional Networks

2 code implementations19 Jun 2019 Jun Zhang, Yamei Liu, Shengping Zhang, Ronald Poppe, Meng Wang

Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light.

Saliency Detection

Learning Clustered Representation for Complex Free Energy Landscapes

no code implementations7 Jun 2019 Jun Zhang, Yao-Kun Lei, Xing Che, Zhen Zhang, Yi Isaac Yang, Yi Qin Gao

In this paper we first analyzed the inductive bias underlying the data scattered across complex free energy landscapes (FEL), and exploited it to train deep neural networks which yield reduced and clustered representation for the FEL.

Dimensionality Reduction

Mobile Edge Intelligence and Computing for the Internet of Vehicles

no code implementations2 Jun 2019 Jun Zhang, Khaled B. Letaief

The Internet of Vehicles (IoV) is an emerging paradigm, driven by recent advancements in vehicular communications and networking.

Networking and Internet Architecture Signal Processing

Client-Edge-Cloud Hierarchical Federated Learning

1 code implementation16 May 2019 Lumin Liu, Jun Zhang, S. H. Song, Khaled B. Letaief

To combine their advantages, we propose a client-edge-cloud hierarchical Federated Learning system, supported with a HierFAVG algorithm that allows multiple edge servers to perform partial model aggregation.

Federated Learning

DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks

1 code implementation12 May 2019 Jun Zhang, Tong Zheng, Shengping Zhang, Meng Wang

First, the contextual net with a center-surround architecture extracts local contextual features from image patches, and generates initial illuminant estimates and the corresponding color corrected patches.

Color Constancy

The Roadmap to 6G -- AI Empowered Wireless Networks

no code implementations26 Apr 2019 Khaled B. Letaief, Wei Chen, Yuanming Shi, Jun Zhang, Ying-Jun Angela Zhang

The recent upsurge of diversified mobile applications, especially those supported by Artificial Intelligence (AI), is spurring heated discussions on the future evolution of wireless communications.

Topological Persistence in Geometry and Analysis

no code implementations8 Apr 2019 Leonid Polterovich, Daniel Rosen, Karina Samvelyan, Jun Zhang

The theory of persistence modules is an emerging field of algebraic topology which originated in topological data analysis.

Algebraic Topology Classical Analysis and ODEs Symplectic Geometry 55U99, 58Cxx, 53Dxx

Hybrid Beamforming for Millimeter Wave Systems Using the MMSE Criterion

2 code implementations22 Feb 2019 Tian Lin, Jiaqi Cong, Yu Zhu, Jun Zhang, Khaled B. Letaief

A particular innovation in our proposed alternating minimization algorithms is a carefully designed initialization method, which leads to faster convergence.

Information Theory Information Theory

On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions

no code implementations4 Jan 2019 Rongrong Lin, Haizhang Zhang, Jun Zhang

We explore a generic definition of RKBS and the reproducing kernel for RKBS that is independent of construction.

LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples

no code implementations18 Dec 2018 Yifei Shen, Yuanming Shi, Jun Zhang, Khaled B. Letaief

To further address the task mismatch problem, we develop a transfer learning method via self-imitation in LORM, named LORM-TL, which can quickly adapt a pre-trained machine learning model to the new task with only a few additional unlabeled training samples.

Imitation Learning Transfer Learning

Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission

no code implementations5 Dec 2018 Dongzhu Liu, Guangxu Zhu, Jun Zhang, Kaibin Huang

To solve the problem, a new retransmission protocol called data-importance aware automatic-repeat-request (importance ARQ) is proposed.

Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks

no code implementations17 Nov 2018 Yifei Shen, Yuanming Shi, Jun Zhang, Khaled B. Letaief

A unique advantage of the proposed method is that it can tackle the task mismatch issue with a few additional unlabeled training samples, which is especially important when transferring to large-size problems.

Transfer Learning

Session-level Language Modeling for Conversational Speech

no code implementations EMNLP 2018 Wayne Xiong, Lingfeng Wu, Jun Zhang, Andreas Stolcke

We propose to generalize language models for conversational speech recognition to allow them to operate across utterance boundaries and speaker changes, thereby capturing conversation-level phenomena such as adjacency pairs, lexical entrainment, and topical coherence.

Speech Recognition

Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration

2 code implementations10 Sep 2018 Jun Zhang

Deformable image registration is a fundamental task in medical image analysis, aiming to establish a dense and non-linear correspondence between a pair of images.

Image Registration

Towards an Intelligent Edge: Wireless Communication Meets Machine Learning

no code implementations2 Sep 2018 Guangxu Zhu, Dongzhu Liu, Yuqing Du, Changsheng You, Jun Zhang, Kaibin Huang

Accordingly, a new research area, called edge learning, emerges, which crosses and revolutionizes two disciplines: wireless communication and machine learning.

Edge-computing

Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection

no code implementations10 Aug 2018 Xiao Chen, Chaoran Li, Derui Wang, Sheng Wen, Jun Zhang, Surya Nepal, Yang Xiang, Kui Ren

In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning based detectors that rely on semantic features such as control-flow-graph.

Cryptography and Security

Automatic deep learning-based normalization of breast dynamic contrast-enhanced magnetic resonance images

no code implementations5 Jul 2018 Jun Zhang, Ashirbani Saha, Brian J. Soher, Maciej A. Mazurowski

Then, based on the segmentation results, a subject-specific piecewise linear mapping function was applied between the anchor points to normalize the same type of tissue in different patients into the same intensity ranges.

Automated Big Traffic Analytics for Cyber Security

no code implementations24 Apr 2018 Yuantian Miao, Zichan Ruan, Lei Pan, Yu Wang, Jun Zhang, Yang Xiang

Network traffic analytics technology is a cornerstone for cyber security systems.

Cryptography and Security

Deep Nearest Class Mean Model for Incremental Odor Classification

no code implementations8 Jan 2018 Yu Cheng, Angus Wong, Kevin Hung, Zhizhong Li, Weitong Li, Jun Zhang

That is, the odor datasets are dynamically growing while both training samples and number of classes are increasing over time.

Classification General Classification

Deep Learning for identifying radiogenomic associations in breast cancer

no code implementations29 Nov 2017 Zhe Zhu, Ehab AlBadawy, Ashirbani Saha, Jun Zhang, Michael R. Harowicz, Maciej A. Mazurowski

Results: The best AUC performance for distinguishing molecular subtypes was 0. 65 (95% CI:[0. 57, 0. 71]) and was achieved by the off-the-shelf deep features approach.

Transfer Learning

Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ

no code implementations28 Nov 2017 Zhe Zhu, Michael Harowicz, Jun Zhang, Ashirbani Saha, Lars J. Grimm, E. Shelley Hwang, Maciej A. Mazurowski

In the first approach, we adopted the transfer learning strategy, in which a network pre-trained on a large dataset of natural images is fine-tuned with our DCIS images.

Transfer Learning

When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual Behavioral Infectivity

no code implementations14 Oct 2017 Tong Chen, Lin Wu, Yang Wang, Jun Zhang, Hongxu Chen, Xue Li

Inspired by point process in modeling temporal point process, in this paper we present a deep prediction method based on two recurrent neural networks (RNNs) to jointly model each user's continuous browsing history and asynchronous event sequences in the context of inter-user behavioral mutual infectivity.

Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model

no code implementations17 May 2017 Xu Tian, Jun Zhang, Zejun Ma, Yi He, Juan Wei

The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding.

Frame General Classification

Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection

no code implementations20 Apr 2017 Tong Chen, Lin Wu, Xue Li, Jun Zhang, Hongzhi Yin, Yang Wang

The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time.

Deep Attention

Deep LSTM for Large Vocabulary Continuous Speech Recognition

no code implementations21 Mar 2017 Xu Tian, Jun Zhang, Zejun Ma, Yi He, Juan Wei, Peihao Wu, Wenchang Situ, Shuai Li, Yang Zhang

It is a competitive framework that LSTM models of more than 7 layers are successfully trained on Shenma voice search data in Mandarin and they outperform the deep LSTM models trained by conventional approach.

Speech Recognition Transfer Learning

Exponential Moving Average Model in Parallel Speech Recognition Training

no code implementations3 Mar 2017 Xu Tian, Jun Zhang, Zejun Ma, Yi He, Juan Wei

As training data rapid growth, large-scale parallel training with multi-GPUs cluster is widely applied in the neural network model learning currently. We present a new approach that applies exponential moving average method in large-scale parallel training of neural network model.

Speech Recognition

Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point clouds

no code implementations17 Feb 2017 Hamid Hamraz, Marco A. Contreras, Jun Zhang

Existing segmentation procedures typically detect more than 90% of overstory trees, yet they barely detect 60% of understory trees because of the occlusion effect of higher canopy layers.

A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data

no code implementations1 Jan 2017 Hamid Hamraz, Marco A. Contreras, Jun Zhang

This paper presents a non-parametric approach for segmenting trees from airborne LiDAR data in deciduous forests.

Vertical stratification of forest canopy for segmentation of under-story trees within small-footprint airborne LiDAR point clouds

no code implementations31 Dec 2016 Hamid Hamraz, Marco A. Contreras, Jun Zhang

This paper presents a tree segmentation approach for multi-story stands that stratifies the point cloud to canopy layers and segments individual tree crowns within each layer using a digital surface model based tree segmentation method.

Power Data Classification: A Hybrid of a Novel Local Time Warping and LSTM

no code implementations15 Aug 2016 Yuanlong Li, Han Hu, Yonggang Wen, Jun Zhang

Finally, using the power consumption data from a real data center, we show that the proposed LTW can improve the classification accuracy of DTW from about 84% to 90%.

Classification General Classification +2

Dynamic Computation Offloading for Mobile-Edge Computing with Energy Harvesting Devices

no code implementations18 May 2016 Yuyi Mao, Jun Zhang, Khaled B. Letaief

Sample simulation results shall be presented to verify the theoretical analysis as well as validate the effectiveness of the proposed algorithm.

Information Theory Information Theory

Agglomerative clustering and collectiveness measure via exponent generating function

no code implementations30 Jul 2015 Wei-Ya Ren, Shuo-Hao Li, Qiang Guo, Guo-Hui Li, Jun Zhang

A novel agglomerative clustering method is proposed by utilizing the path integral to define the affinity measure.

Implementation of Training Convolutional Neural Networks

no code implementations3 Jun 2015 Tianyi Liu, Shuangsang Fang, Yuehui Zhao, Peng Wang, Jun Zhang

Deep learning refers to the shining branch of machine learning that is based on learning levels of representations.

Face Recognition

Performance Analysis on Evolutionary Algorithms for the Minimum Label Spanning Tree Problem

no code implementations3 Sep 2014 Xinsheng Lai, Yuren Zhou, Jun He, Jun Zhang

We also show that GSEMO achieves a $(2ln(n))$-approximation ratio for the MLST problem in expected polynomial time of $n$ and $k$.

Real-Time Traffic Signal Control for Modern Roundabouts by Using Particle Swarm Optimization-Based Fuzzy Controller

no code implementations4 Aug 2014 Yue-Jiao Gong, Jun Zhang

This mechanism helps to instantly respond to the current traffic condition of the roundabout so as to improve real-timeness.

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