Search Results for author: Di wu

Found 130 papers, 37 papers with code

A Read Margin Enhancement Circuit with Dynamic Bias Optimization for MRAM

no code implementations18 Sep 2023 Renhe Chen, Albert Lee, ZiRui Wang, Di wu, Xufeng Kou

This brief introduces a read bias circuit to improve readout yield of magnetic random access memories (MRAMs).

Virtual histological staining of unlabeled autopsy tissue

no code implementations2 Aug 2023 Yuzhu Li, Nir Pillar, Jingxi Li, Tairan Liu, Di wu, Songyu Sun, Guangdong Ma, Kevin De Haan, Luzhe Huang, Sepehr Hamidi, Anatoly Urisman, Tal Keidar Haran, William Dean Wallace, Jonathan E. Zuckerman, Aydogan Ozcan

Histological examination is a crucial step in an autopsy; however, the traditional histochemical staining of post-mortem samples faces multiple challenges, including the inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, as well as the resource-intensive nature of chemical staining procedures covering large tissue areas, which demand substantial labor, cost, and time.

Image Registration

Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes

1 code implementation22 Jul 2023 Di wu, Pengfei Chen, Xuehui Yu, Guorong Li, Zhenjun Han, Jianbin Jiao

Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects).

Multiple Instance Learning object-detection +1

On-the-fly machine learning for parametrization of the effective Hamiltonian

no code implementations18 Jul 2023 Xingyue Ma, L. Bellaiche, Di wu, Yurong Yang

The first-principles-based effective Hamiltonian is widely used to predict and simulate the properties of ferroelectrics and relaxor ferroelectrics.

CeBed: A Benchmark for Deep Data-Driven OFDM Channel Estimation

1 code implementation23 Jun 2023 Amal Feriani, Di wu, Steve Liu, Greg Dudek

This work offers a comprehensive and unified framework to help researchers evaluate and design data-driven channel estimation algorithms.

Experimental Design

An Error Correction Mid-term Electricity Load Forecasting Model Based on Seasonal Decomposition

no code implementations19 Jun 2023 Liping Zhang, Di wu, Xin Luo

Then, based on the idea of stacking ensemble, long short-term memory is employed as an error correction module to forecast the components separately, and the forecast results are treated as new features to be fed into extreme gradient boosting for the second-step forecasting.

Feature Engineering Load Forecasting +2

Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network

no code implementations31 May 2023 Yan Wang, Feng Shu, Zhihong Zhuang, Rongen Dong, Qi Zhang, Di wu, Liang Yang, Jiangzhou Wang

Numerical simulation results show that a 3-bit discrete phase shifter is required to achieve a trivial performance loss for a large-scale active IRS.

Quantization

Lightweight Learner for Shared Knowledge Lifelong Learning

1 code implementation24 May 2023 Yunhao Ge, Yuecheng Li, Di wu, Ao Xu, Adam M. Jones, Amanda Sofie Rios, Iordanis Fostiropoulos, Shixian Wen, Po-Hsuan Huang, Zachary William Murdock, Gozde Sahin, Shuo Ni, Kiran Lekkala, Sumedh Anand Sontakke, Laurent Itti

We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel.

Image Classification

A new sulfur bioconversion process development for energy- and space-efficient secondary wastewater treatment

no code implementations22 May 2023 Chu-Kuan Jiang, Yang-Fan Deng, Hongxiao Guo, Guang-Hao Chen, Di wu

Typical pretreated wastewater was synthesized with chemical oxygen demand of 110 mg/L, sulfate of 50 mg S/L, and varying dissolved oxygen (DO) and was fed into a moving-bed biofilm reactor (MBBR).

ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs

no code implementations18 May 2023 Xingchen Song, Di wu, BinBin Zhang, Zhendong Peng, Bo Dang, Fuping Pan, Zhiyong Wu

In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \textbf{training-free} methods to decrease the Token Display Time (TDT) of streaming ASR models \textbf{without any accuracy loss}.

FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment

no code implementations10 May 2023 Jiahao Liu, Jiang Wu, Jinyu Chen, Miao Hu, Yipeng Zhou, Di wu

In this paper, we propose a new PFL algorithm called \emph{FedDWA (Federated Learning with Dynamic Weight Adjustment)} to address the above problem, which leverages the parameter server (PS) to compute personalized aggregation weights based on collected models from clients.

Personalized Federated Learning

BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learning

no code implementations9 May 2023 Yunchao Yang, Yipeng Zhou, Miao Hu, Di wu, Quan Z. Sheng

The challenge of this problem lies in the opaque feedback between reward budget allocation and model utility improvement of FL, making the optimal reward budget allocation complicated.

Bayesian Optimization Federated Learning

KPEval: Towards Fine-grained Semantic-based Evaluation of Keyphrase Extraction and Generation Systems

no code implementations27 Mar 2023 Di wu, Da Yin, Kai-Wei Chang

Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation only relies on exact matching with human references and disregards reference-free attributes.

Keyphrase Extraction Keyphrase Generation

Edge-Based Video Analytics: A Survey

no code implementations25 Mar 2023 Miao Hu, Zhenxiao Luo, Amirmohammad Pasdar, Young Choon Lee, Yipeng Zhou, Di wu

Edge computing has been getting a momentum with ever-increasing data at the edge of the network.

Cloud Computing Edge-computing +1

From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding

no code implementations22 Mar 2023 Borui Cai, Yong Xiang, Longxiang Gao, Di wu, He Zhang, Jiong Jin, Tom Luan

Specifically, we view the concatenation of all entity representations as an embedding layer, and then conventional KGE methods that adopt high-dimensional entity representations equal to enlarging the width of the embedding layer to gain expressiveness.

Knowledge Distillation Knowledge Graph Embedding +1

Communication Load Balancing via Efficient Inverse Reinforcement Learning

no code implementations22 Mar 2023 Abhisek Konar, Di wu, Yi Tian Xu, Seowoo Jang, Steve Liu, Gregory Dudek

Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function.

reinforcement-learning Reinforcement Learning (RL)

Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarios

no code implementations22 Mar 2023 Yi Tian Xu, Jimmy Li, Di wu, Michael Jenkin, Seowoo Jang, Xue Liu, Gregory Dudek

When deploying to an unknown traffic scenario, we select a policy from the policy bank based on the similarity between the previous-day traffic of the current scenario and the traffic observed during training.

Reinforcement Learning (RL)

Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks

no code implementations14 Mar 2023 Jikun Kang, Di wu, Ju Wang, Ekram Hossain, Xue Liu, Gregory Dudek

In cellular networks, User Equipment (UE) handoff from one Base Station (BS) to another, giving rise to the load balancing problem among the BSs.

Online Sparse Streaming Feature Selection Using Adapted Classification

no code implementations25 Feb 2023 Ruiyang Xu, Di wu, Xin Luo

Traditional feature selections need to know the feature space before learning, and online streaming feature selection (OSFS) is proposed to process streaming features on the fly.

Classification feature selection

Adaptive Aggregation for Safety-Critical Control

no code implementations7 Feb 2023 Huiliang Zhang, Di wu, Benoit Boulet

Safety has been recognized as the central obstacle to preventing the use of reinforcement learning (RL) for real-world applications.

reinforcement-learning Reinforcement Learning (RL) +2

Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks

no code implementations3 Feb 2023 Igor Kozlov, Dmitriy Rivkin, Wei-Di Chang, Di wu, Xue Liu, Gregory Dudek

Such networks undergo frequent and often heterogeneous changes caused by network operators, who are seeking to tune their system parameters for optimal performance.

Change Detection Self-Supervised Learning

A Novel Modular, Reconfigurable Battery Energy Storage System: Design, Control, and Experimentation

no code implementations12 Jan 2023 Amir Farakhor, Di wu, Yebin Wang, Huazhen Fang

An optimal power management approach is developed to extensively exploit the merits of the proposed design.

Management

Original or Translated? On the Use of Parallel Data for Translation Quality Estimation

no code implementations20 Dec 2022 Baopu Qiu, Liang Ding, Di wu, Lin Shang, Yibing Zhan, DaCheng Tao

Machine Translation Quality Estimation (QE) is the task of evaluating translation output in the absence of human-written references.

Data Augmentation Machine Translation +1

Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study

1 code implementation20 Dec 2022 Di wu, Wasi Uddin Ahmad, Kai-Wei Chang

However, there lacks a systematic study of how the two types of approaches compare and how different design choices can affect the performance of PLM-based models.

Keyphrase Extraction Keyphrase Generation

Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction

no code implementations20 Dec 2022 Cheng Liang, Teng Huang, Yi He, Song Deng, Di wu, Xin Luo

The idea of the proposed MMA is mainly two-fold: 1) apply different $L_p$-norm on loss function and regularization to form different variant models in different metric spaces, and 2) aggregate these variant models.

Recommendation Systems

Design Considerations of a Coordinative Demand Charge Mitigation Strategy

no code implementations16 Dec 2022 Rongxing Hu, Kai Ye, Hyeonjin Kim, Hanpyo Lee, Ning Lu, Di wu, PJ Rehm

This paper presents a coordinative demand charge mitigation (DCM) strategy for reducing electricity consumption during system peak periods.

energy management Management

Relightable Neural Human Assets from Multi-view Gradient Illuminations

no code implementations CVPR 2023 Taotao Zhou, Kai He, Di wu, Teng Xu, Qixuan Zhang, Kuixiang Shao, Wenzheng Chen, Lan Xu, Jingyi Yu

UltraStage will be publicly available to the community to stimulate significant future developments in various human modeling and rendering tasks.

Image Relighting Novel View Synthesis

A Modified Sequence-to-point HVAC Load Disaggregation Algorithm

no code implementations9 Dec 2022 Kai Ye, Hyeonjin Kim, Yi Hu, Ning Lu, Di wu, PJ Rehm

This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption.

Dual Class-Aware Contrastive Federated Semi-Supervised Learning

no code implementations16 Nov 2022 Qi Guo, Yong Qi, Saiyu Qi, Di wu

To our knowledge, we are the first to present an FSSL method that utilizes only 10\% labeled clients, while still achieving superior performance compared to standard federated supervised learning, which uses all clients with labeled data.

Efficient Multi-order Gated Aggregation Network

4 code implementations7 Nov 2022 Siyuan Li, Zedong Wang, Zicheng Liu, Cheng Tan, Haitao Lin, Di wu, ZhiYuan Chen, Jiangbin Zheng, Stan Z. Li

Since the recent success of Vision Transformers (ViTs), explorations toward ViT-style architectures have triggered the resurgence of ConvNets.

 Ranked #1 on Instance Segmentation on COCO test-dev (AP50 metric)

3D Human Pose Estimation Image Classification +5

An Iterative Bidirectional Gradient Boosting Algorithm for CVR Baseline Estimation

no code implementations7 Nov 2022 Han Pyo Lee, Lidong Song, Yiyan Li, Ning Lu, Di wu, PJ Rehm, Matthew Makdad, Edmond Miller

The proposed algorithm consists of two key steps: selection of similar days and iterative bidirectional-GB training.

TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty

2 code implementations1 Nov 2022 Xingchen Song, Di wu, Zhiyong Wu, BinBin Zhang, Yuekai Zhang, Zhendong Peng, Wenpeng Li, Fuping Pan, Changbao Zhu

In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models.

Deep Koopman Learning of Nonlinear Time-Varying Systems

no code implementations12 Oct 2022 Wenjian Hao, Bowen Huang, Wei Pan, Di wu, Shaoshuai Mou

This paper presents a data-driven approach to approximate the dynamics of a nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), which is resulted from the Koopman operator and deep neural networks.

Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond

no code implementations3 Oct 2022 Di wu, Jie Yang, Mohamad Sawan

In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications.

Electromyography (EMG) Transfer Learning

An ICA-Based HVAC Load Disaggregation Method Using Smart Meter Data

no code implementations19 Sep 2022 Hyeonjin Kim, Kai Ye, Han Pyo Lee, Rongxing Hu, Ning Lu, Di wu, PJ Rehm

The residual load profiles are processed using ICA for HVAC load extraction.

OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning

1 code implementation11 Sep 2022 Siyuan Li, Zedong Wang, Zicheng Liu, Di wu, Stan Z. Li

With the remarkable progress of deep neural networks in computer vision, data mixing augmentation techniques are widely studied to alleviate problems of degraded generalization when the amount of training data is limited.

Representation Learning Self-Supervised Learning +1

DPAUC: Differentially Private AUC Computation in Federated Learning

1 code implementation25 Aug 2022 Jiankai Sun, Xin Yang, Yuanshun Yao, Junyuan Xie, Di wu, Chong Wang

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants.

Federated Learning

FedMCSA: Personalized Federated Learning via Model Components Self-Attention

no code implementations23 Aug 2022 Qi Guo, Yong Qi, Saiyu Qi, Di wu, Qian Li

Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data.

Personalized Federated Learning

A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery

no code implementations16 Aug 2022 Yuting Ding, Di wu

In the past decade, scholars have done many research on the recovery of missing traffic data, however how to make full use of spatio-temporal traffic patterns to improve the recovery performance is still an open problem.

Matrix Completion

Optimal Measurement of Drone Swarm in RSS-based Passive Localization with Region Constraints

no code implementations2 Aug 2022 Xin Cheng, Feng Shu, YiFan Li, Zhihong Zhuang, Di wu, Jiangzhou Wang

In this paper, optimal geometrical configurations of UAVs in received signal strength (RSS)-based localization under region constraints are investigated.

An Online Sparse Streaming Feature Selection Algorithm

no code implementations2 Aug 2022 Feilong Chen, Di wu, Jie Yang, Yi He

In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i. e., how to establish the uncertain relationship between sparse streaming features and labels.

feature selection

Energy Storage State-of-Charge Market Model

no code implementations14 Jul 2022 Ningkun Zheng, Xin Qin, Di wu, Gabe Murtaugh, Bolun Xu

Combined with an optimal bidding design algorithm using dynamic programming, our paper shows that the SoC segment market model provides more accurate representations of the opportunity costs of energy storage compared to existing power-based bidding models.

DLME: Deep Local-flatness Manifold Embedding

2 code implementations7 Jul 2022 Zelin Zang, Siyuan Li, Di wu, Ge Wang, Lei Shang, Baigui Sun, Hao Li, Stan Z. Li

To overcome the underconstrained embedding problem, we design a loss and theoretically demonstrate that it leads to a more suitable embedding based on the local flatness.

Contrastive Learning Data Augmentation +1

Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting

no code implementations AAAI Conference on Artificial Intelligence 2022 Yuwei Fu, Di wu, Benoit Boulet

To deal with this challenge, we propose a reinforcement learning (RL) based model combination (RLMC) framework for determining model weights in an ensemble for time series forecasting tasks.

Decision Making Ensemble Learning +6

HIFI-Net: A Novel Network for Enhancement to Underwater Images

no code implementations6 Jun 2022 Jiajia Zhou, Junbin Zhuang, Yan Zheng, Di wu

As this network make "Haar Images into Fusion Images", it is called HIFI-Net.

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

3 code implementations27 May 2022 Siyuan Li, Di wu, Fang Wu, Zelin Zang, Stan. Z. Li

We then propose an Architecture-Agnostic Masked Image Modeling framework (A$^2$MIM), which is compatible with both Transformers and CNNs in a unified way.

Instance Segmentation Object Detection +3

MALICE: Manipulation Attacks on Learned Image ComprEssion

no code implementations26 May 2022 Kang Liu, Di wu, Yiru Wang, Dan Feng, Benjamin Tan, Siddharth Garg

To characterize the robustness of state-of-the-art learned image compression, we mount white-box and black-box attacks.

Image Compression Image Reconstruction

Differentially Private AUC Computation in Vertical Federated Learning

no code implementations24 May 2022 Jiankai Sun, Xin Yang, Yuanshun Yao, Junyuan Xie, Di wu, Chong Wang

In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.

Federated Learning

Time Series Anomaly Detection via Reinforcement Learning-Based Model Selection

1 code implementation19 May 2022 Jiuqi Elise Zhang, Di wu, Benoit Boulet

Time series anomaly detection has been recognized as of critical importance for the reliable and efficient operation of real-world systems.

Anomaly Detection Model Selection +4

An Early Fault Detection Method of Rotating Machines Based on Multiple Feature Fusion with Stacking Architecture

no code implementations1 May 2022 Wenbin Song, Di wu, Weiming Shen, Benoit Boulet

One of the key points of EFD is developing a generic model to extract robust and discriminative features from different equipment for early fault detection.

Denoising Fault Detection

Meta-Learning Based Early Fault Detection for Rolling Bearings via Few-Shot Anomaly Detection

no code implementations27 Apr 2022 Wenbin Song, Di wu, Weiming Shen, Benoit Boulet

To address this problem, many transfer learning based EFD methods utilize historical data to learn transferable domain knowledge and conduct early fault detection on new target bearings.

Anomaly Detection Fault Detection +3

neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning

1 code implementation20 Apr 2022 Di wu, Siyuan Li, Jie Yang, Mohamad Sawan

Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.

EEG Electroencephalogram (EEG) +3

Graph-incorporated Latent Factor Analysis for High-dimensional and Sparse Matrices

no code implementations16 Apr 2022 Di wu, Yi He, Xin Luo

A High-dimensional and sparse (HiDS) matrix is frequently encountered in a big data-related application like an e-commerce system or a social network services system.

Representation Learning Vocal Bursts Intensity Prediction

A Multi-Metric Latent Factor Model for Analyzing High-Dimensional and Sparse data

no code implementations16 Apr 2022 Di wu, Peng Zhang, Yi He, Xin Luo

High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications.

Representation Learning

A Differential Evolution-Enhanced Latent Factor Analysis Model for High-dimensional and Sparse Data

no code implementations2 Apr 2022 Jia Chen, Di wu, Xin Luo

High-dimensional and sparse (HiDS) matrices are frequently adopted to describe the complex relationships in various big data-related systems and applications.

WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

3 code implementations29 Mar 2022 BinBin Zhang, Di wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao, Hang Lv, Lei Xie, Chao Yang, Fuping Pan, Jianwei Niu

Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.

Language Modelling speech-recognition +1

Predicting Peak Day and Peak Hour of Electricity Demand with Ensemble Machine Learning

no code implementations25 Mar 2022 Tao Fu, Huifen Zhou, Xu Ma, Z. Jason Hou, Di wu

In this study, we develop a supervised machine learning approach to generate 1) the probability of the next operation day containing the peak hour of the month and 2) the probability of an hour to be the peak hour of the day.

BIG-bench Machine Learning Decision Making

Object Localization under Single Coarse Point Supervision

2 code implementations CVPR 2022 Xuehui Yu, Pengfei Chen, Di wu, Najmul Hassan, Guorong Li, Junchi Yan, Humphrey Shi, Qixiang Ye, Zhenjun Han

In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.

Multiple Instance Learning Object Localization

Representation Learning for Resource-Constrained Keyphrase Generation

1 code implementation15 Mar 2022 Di wu, Wasi Uddin Ahmad, Sunipa Dev, Kai-Wei Chang

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data.

Denoising Domain Adaptation +4

Impression Allocation and Policy Search in Display Advertising

no code implementations11 Mar 2022 Di wu, Cheng Chen, Xiujun Chen, Junwei Pan, Xun Yang, Qing Tan, Jian Xu, Kuang-Chih Lee

In order to address the unstable traffic pattern challenge and achieve the optimal overall outcome, we propose a multi-agent reinforcement learning method to adjust the bids from each guaranteed contract, which is simple, converging efficiently and scalable.

Multi-agent Reinforcement Learning

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

no code implementations25 Feb 2022 Di wu, Jie Yang, Mohamad Sawan

The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.

Knowledge Distillation Seizure prediction

Learning to Simulate Unseen Physical Systems with Graph Neural Networks

no code implementations NeurIPS Workshop AI4Scien 2021 Ce Yang, Weihao Gao, Di wu, Chong Wang

Simulation of the dynamics of physical systems is essential to the development of both science and engineering.

Gap Minimization for Knowledge Sharing and Transfer

no code implementations26 Jan 2022 Boyu Wang, Jorge Mendez, Changjian Shui, Fan Zhou, Di wu, Gezheng Xu, Christian Gagné, Eric Eaton

Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.

Representation Learning Transfer Learning

Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand

1 code implementation8 Jan 2022 Arec Jamgochian, Di wu, Kunal Menda, Soyeon Jung, Mykel J. Kochenderfer

In this paper, we introduce the conditional approximate normalizing flow (CANF) to make probabilistic multi-step time-series forecasts when correlations are present over long time horizons.

Decision Making Scheduling +2

P2P-Loc: Point to Point Tiny Person Localization

no code implementations31 Dec 2021 Xuehui Yu, Di wu, Qixiang Ye, Jianbin Jiao, Zhenjun Han

As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way.

Object Localization

Constrained Adaptive Projection with Pretrained Features for Anomaly Detection

1 code implementation5 Dec 2021 Xingtai Gui, Di wu, Yang Chang, Shicai Fan

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection.

Anomaly Detection

FedFly: Towards Migration in Edge-based Distributed Federated Learning

1 code implementation2 Nov 2021 Rehmat Ullah, Di wu, Paul Harvey, Peter Kilpatrick, Ivor Spence, Blesson Varghese

Our empirical results on the CIFAR10 dataset, with both balanced and imbalanced data distribution, support our claims that FedFly can reduce training time by up to 33% when a device moves after 50% of the training is completed, and by up to 45% when 90% of the training is completed when compared to state-of-the-art offloading approach in FL.

Federated Learning Privacy Preserving

GenURL: A General Framework for Unsupervised Representation Learning

1 code implementation27 Oct 2021 Siyuan Li, Zicheng Liu, Zelin Zang, Di wu, ZhiYuan Chen, Stan Z. Li

Unsupervised representation learning (URL) that learns compact embeddings of high-dimensional data without supervision has achieved remarkable progress recently.

Contrastive Learning Dimensionality Reduction +4

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

no code implementations26 Oct 2021 Di wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan

Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.

Compressive Sensing Seizure prediction

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

1 code implementation7 Oct 2021 BinBin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di wu, Zhendong Peng

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.

Label Error Detection Optical Character Recognition +4

Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning

no code implementations29 Sep 2021 Di wu, Tianyu Li, David Meger, Michael Jenkin, Xue Liu, Gregory Dudek

Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.

Continuous Control Imitation Learning +3

Improving Discriminative Visual Representation Learning via Automatic Mixup

no code implementations29 Sep 2021 Siyuan Li, Zicheng Liu, Di wu, Stan Z. Li

In this paper, we decompose mixup into two sub-tasks of mixup generation and classification and formulate it for discriminative representations as class- and instance-level mixup.

Data Augmentation Representation Learning

Benchmarking Sample Selection Strategies for Batch Reinforcement Learning

no code implementations29 Sep 2021 Yuwei Fu, Di wu, Benoit Boulet

Through extensive experiments on the standard batch RL datasets, we find that non-uniform sampling is also effective in batch RL settings.

Benchmarking Imitation Learning +2

Improving Neural Machine Translation by Bidirectional Training

no code implementations EMNLP 2021 Liang Ding, Di wu, DaCheng Tao

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation.

Machine Translation Translation

Time Series Anomaly Detection for Smart Grids: A Survey

no code implementations16 Jul 2021 Jiuqi, Zhang, Di wu, Benoit Boulet

With the rapid increase in the integration of renewable energy generation and the wide adoption of various electric appliances, power grids are now faced with more and more challenges.

Anomaly Detection Time Series +1

FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning

1 code implementation9 Jul 2021 Di wu, Rehmat Ullah, Paul Harvey, Peter Kilpatrick, Ivor Spence, Blesson Varghese

Further, FedAdapt adopts reinforcement learning based optimization and clustering to adaptively identify which layers of the DNN should be offloaded for each individual device on to a server to tackle the challenges of computational heterogeneity and changing network bandwidth.

Federated Learning

Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy

1 code implementation5 Jul 2021 Yipeng Zhou, Xuezheng Liu, Yao Fu, Di wu, Chao Li, Shui Yu

In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized.

Federated Learning

Data-driven Model Predictive and Reinforcement Learning Based Control for Building Energy Management: a Survey

no code implementations28 Jun 2021 Huiliang Zhang, Sayani Seal, Di wu, Benoit Boulet, Francois Bouffard, Geza Joos

Building energy management is one of the core problems in modern power grids to reduce energy consumption while ensuring occupants' comfort.

energy management Management +2

U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

no code implementations10 Jun 2021 Di wu, BinBin Zhang, Chao Yang, Zhendong Peng, Wenjing Xia, Xiaoyu Chen, Xin Lei

On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.

Data Augmentation speech-recognition +1

Unsupervised Deep Manifold Attributed Graph Embedding

1 code implementation27 Apr 2021 Zelin Zang, Siyuan Li, Di wu, Jianzhu Guo, Yongjie Xu, Stan Z. Li

Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.

Clustering Graph Embedding +3

Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis

no code implementations22 Apr 2021 Di wu, XiaoFeng Xie, Xiang Ni, Bin Fu, Hanhui Deng, Haibo Zeng, Zhijin Qin

We further present an experiment on data anomaly detection in this architecture, and the comparison between two architectures for ECG diagnosis.

Anomaly Detection Edge-computing

Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding

no code implementations13 Apr 2021 Di wu, Yiren Chen, Liang Ding, DaCheng Tao

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +7

Representation range needs for 16-bit neural network training

no code implementations29 Mar 2021 Valentina Popescu, Abhinav Venigalla, Di wu, Robert Schreiber

While neural networks have been trained using IEEE-754 binary32 arithmetic, the rapid growth of computational demands in deep learning has boosted interest in faster, low precision training.

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

2 code implementations24 Mar 2021 Zicheng Liu, Siyuan Li, Di wu, Zihan Liu, ZhiYuan Chen, Lirong Wu, Stan Z. Li

Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.

Classification Data Augmentation +3

Virtual Reality: A Survey of Enabling Technologies and its Applications in IoT

no code implementations11 Mar 2021 Miao Hu, Xianzhuo Luo, Jiawen Chen, Young Choon Lee, Yipeng Zhou, Di wu

Virtual Reality (VR) has shown great potential to revolutionize the market by providing users immersive experiences with freedom of movement.

Networking and Internet Architecture

Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models

1 code implementation7 Mar 2021 Linghan Meng, Yanhui Li, Lin Chen, Zhi Wang, Di wu, Yuming Zhou, Baowen Xu

To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.

Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map

no code implementations19 Feb 2021 Di wu, Yong Zeng, Shi Jin, Rui Zhang

Two instances of CKM are proposed for beam alignment in mmWave massive MIMO systems, namely channel path map (CPM) and beam index map (BIM).

WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

3 code implementations2 Feb 2021 Zhuoyuan Yao, Di wu, Xiong Wang, BinBin Zhang, Fan Yu, Chao Yang, Zhendong Peng, Xiaoyu Chen, Lei Xie, Xin Lei

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.

speech-recognition Speech Recognition

On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times

no code implementations11 Jan 2021 Yao Fu, Yipeng Zhou, Di wu, Shui Yu, Yonggang Wen, Chao Li

Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.

Federated Learning

Unsupervised Word Alignment via Cross-Lingual Contrastive Learning

no code implementations1 Jan 2021 Di wu, Liang Ding, Shuo Yang, DaCheng Tao

Recently, the performance of the neural word alignment models has exceeded that of statistical models.

Contrastive Learning Translation +1

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

4 code implementations10 Dec 2020 BinBin Zhang, Di wu, Zhuoyuan Yao, Xiong Wang, Fan Yu, Chao Yang, Liyong Guo, Yaguang Hu, Lei Xie, Xin Lei

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.

speech-recognition Speech Recognition

Context-Aware Cross-Attention for Non-Autoregressive Translation

1 code implementation COLING 2020 Liang Ding, Longyue Wang, Di wu, DaCheng Tao, Zhaopeng Tu

Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence.

Translation

Network Anomaly Detection Using Federated Learning and Transfer Learning

no code implementations International Conference on Security and Privacy in Digital Economy 2020 Ying Zhao, Junjun Chen, Qianling Guo, Jian Teng, Di wu

In the second learning stage, Ot uses the transfer learning method to reconstruct and re-train the model to further improve the detection performance on the specific task.

Anomaly Detection Federated Learning +1

From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security

no code implementations19 Oct 2020 Sheng Shen, Tianqing Zhu, Di wu, Wei Wang, Wanlei Zhou

Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.

Distributed, Parallel, and Cluster Computing

End-to-End Learning for Simultaneously Generating Decision Map and Multi-Focus Image Fusion Result

2 code implementations17 Oct 2020 Boyuan Ma, Xiang Yin, Di wu, Xiaojuan Ban

In this work, to handle the requirements of both output image quality and comprehensive simplicity of structure implementation, we propose a cascade network to simultaneously generate decision map and fused result with an end-to-end training procedure.

2D Cyclist Detection

When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network

no code implementations22 Sep 2020 Shuai Yu, Xu Chen, Zhi Zhou, Xiaowen Gong, Di wu

Ultra-dense edge computing (UDEC) has great potential, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: i) efficient utilization of multiple 5G resources (e. g., computation, communication, storage and service resources); ii) low overhead offloading decision making and resource allocation strategies; and iii) privacy and security protection schemes.

Decision Making Edge-computing +2

EasyQuant: Post-training Quantization via Scale Optimization

1 code implementation30 Jun 2020 Di Wu, Qi Tang, Yongle Zhao, Ming Zhang, Ying Fu, Debing Zhang

The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.

Quantization

Energy Model for UAV Communications: Experimental Validation and Model Generalization

no code implementations4 May 2020 Ning Gao, Yong Zeng, Jian Wang, Di wu, Chaoyue Zhang, Qingheng Song, Jiachen Qian, Shi Jin

In this paper, via extensive flight experiments, we aim to firstly validate the recently derived theoretical energy model for rotary-wing UAVs, and then develop a general model for those complicated flight scenarios where rigorous theoretical model derivation is quite challenging, if not impossible.

Neural Mesh Refiner for 6-DoF Pose Estimation

no code implementations17 Mar 2020 Di Wu, Yihao Chen, Xianbiao Qi, Yongjian Yu, Weixuan Chen, Rong Xiao

We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation.

Autonomous Driving Instance Segmentation +4

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

no code implementations29 Dec 2019 Mostafa Karimi, Di wu, Zhangyang Wang, Yang shen

DeepRelations shows superior interpretability to the state-of-the-art: without compromising affinity prediction, it boosts the AUPRC of contact prediction 9. 5, 16. 9, 19. 3 and 5. 7-fold for the test, compound-unique, protein-unique, and both-unique sets, respectively.

BIG-bench Machine Learning Drug Discovery +1

Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification

no code implementations23 Nov 2019 Di Wu, Chao Wang, Yong Wu, De-Shuang Huang

Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network.

Person Re-Identification

Omni-directional Feature Learning for Person Re-identification

no code implementations13 Dec 2018 Di Wu, Hong-Wei Yang, De-Shuang Huang

Most of them focus on learning the part feature representation of person body in horizontal direction.

Person Re-Identification Representation Learning

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition

no code implementations EMNLP 2018 Yufeng Diao, Hongfei Lin, Di wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang

In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.

Random Occlusion-recovery for Person Re-identification

no code implementations26 Sep 2018 Di Wu, Kun Zhang, Fei Cheng, Yang Zhao, Qi Liu, Chang-An Yuan, De-Shuang Huang

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.

Person Re-Identification

Robust and customized methods for real-time hand gesture recognition under object-occlusion

no code implementations16 Sep 2018 Zhishuai Han, Xiaojuan Ban, Xiaokun Wang, Di wu

Dynamic hand tracking and gesture recognition is a hard task since there are many joints on the fingers and each joint owns many degrees of freedom.

Human-Computer Interaction

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

no code implementations10 Sep 2018 Di Wu, Cheng Chen, Xun Yang, Xiujun Chen, Qing Tan, Jian Xu, Kun Gai

With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts.

Multi-agent Reinforcement Learning reinforcement-learning +1

Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising

no code implementations23 Feb 2018 Di Wu, Xiujun Chen, Xun Yang, Hao Wang, Qing Tan, Xiaoxun Zhang, Jian Xu, Kun Gai

Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint.

Marketing reinforcement-learning +1

Machine Learning for Building Energy and Indoor Environment: A Perspective

no code implementations31 Dec 2017 Zhijian Liu, Di wu, Hongyu Wei, Guoqing Cao

It is indicated that the theories and applications of machine learning method in the field of energy conservation and indoor environment are not mature, due to the difficulty of the determination for model structure with better prediction.

BIG-bench Machine Learning

Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition

no code implementations CVPR 2014 Di Wu, Ling Shao

Over the last few years, with the immense popularity of the Kinect, there has been renewed interest in developing methods for human gesture and action recognition from 3D skeletal data.

Action Recognition Action Segmentation +1

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