Search Results for author: Jie Zhang

Found 173 papers, 54 papers with code

Is Self-Attention Powerful to Learn Code Syntax and Semantics?

no code implementations20 Dec 2022 Wei Ma, Mengjie Zhao, Xiaofei Xie, Qiang Hu, Shangqing Liu, Jie Zhang, Wenhan Wang, Yang Liu

We focus on a well-known representative code model, CodeBERT, and study how it can learn code syntax and semantics by the self-attention mechanism and Masked Language Modelling (MLM) at the token level.

Code Completion Code Search +2

Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning

no code implementations19 Dec 2022 Yingchun Wang, Jingcai Guo, Song Guo, Weizhan Zhang, Jie Zhang

Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model.

Out-of-Distribution Generalization

Accelerating Dataset Distillation via Model Augmentation

1 code implementation12 Dec 2022 Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller and high-quality synthetic datasets from large ones.

Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning

no code implementations7 Dec 2022 Yingchun Wang, Song Guo, Jingcai Guo, Weizhan Zhang, Yida Xu, Jie Zhang, Yi Liu

Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.

Network Pruning Variational Inference

Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion

no code implementations29 Nov 2022 Kui Zhang, Hang Zhou, Jie Zhang, Qidong Huang, Weiming Zhang, Nenghai Yu

This approach enables effective defense against adaptive attacks with varying noise budgets, achieving accentuated robustness of existing 3D deep recognition models.

Autonomous Driving Denoising

Boosting Personalised Musculoskeletal Modelling with Physics-informed Knowledge Transfer

no code implementations22 Nov 2022 Jie Zhang, Yihui Zhao, Tianzhe Bao, Zhenhong Li, Kun Qian, Alejandro F. Frangi, Sheng Quan Xie, Zhi-Qiang Zhang

The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model.

Transfer Learning

Decision-making with Imaginary Opponent Models

no code implementations22 Nov 2022 Jing Sun, Shuo Chen, Cong Zhang, Jie Zhang

Specifically, the actor maintains a speculated belief of the opponents, which we call the \textit{imaginary opponent models}, to predict opponents' actions using local observations and makes decisions accordingly.

Decision Making

Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning

no code implementations21 Nov 2022 Xueyang Tang, Song Guo, Jie Zhang

Recently, data heterogeneity among the training datasets on the local clients (a. k. a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it.

Out-of-Distribution Generalization Personalized Federated Learning

VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning

no code implementations21 Nov 2022 Qiushi Zhu, Long Zhou, Ziqiang Zhang, Shujie Liu, Binxing Jiao, Jie Zhang, LiRong Dai, Daxin Jiang, Jinyu Li, Furu Wei

Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e. g., vision, text.

Audio-Visual Speech Recognition Language Modelling +3

Learning to Search for Job Shop Scheduling via Deep Reinforcement Learning

no code implementations20 Nov 2022 Cong Zhang, Wen Song, Zhiguang Cao, Jie Zhang, Puay Siew Tan, Chi Xu

Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics.

Job Shop Scheduling reinforcement-learning +2

FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers

no code implementations15 Nov 2022 Jinyu Chen, Wenchao Xu, Song Guo, Junxiao Wang, Jie Zhang, Haozhao Wang

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.

Federated Learning Language Modelling +1

Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning

no code implementations14 Nov 2022 Yi Liu, Song Guo, Jie Zhang, Qihua Zhou, Yingchun Wang, Xiaohan Zhao

We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.

Federated Learning Knowledge Distillation +3

Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application

no code implementations13 Nov 2022 Leijie Wu, Song Guo, Yaohong Ding, Junxiao Wang, Wenchao Xu, Richard Yida Xu, Jie Zhang

In contrast, visual data exhibits a fundamentally different structure: Its basic unit (pixel) is a natural low-level representation with significant redundancies in the neighbourhood, which poses obvious challenges to the interpretability of MSA mechanism in ViT.

Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams

1 code implementation13 Nov 2022 Kaixin Wang, Cheng Long, Da Yan, Jie Zhang, H. V. Jagadish

Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties.

A Comparative Study on multichannel Speaker-attributed automatic speech recognition in Multi-party Meetings

no code implementations1 Nov 2022 Mohan Shi, Jie Zhang, Zhihao Du, Fan Yu, Shiliang Zhang, Li-Rong Dai

SC-FD-SOT obtains the speaker-attributed transcriptions by aligning the speaker diarization results with the ASR hypotheses, SC-WD-SOT uses word-level diarization to get rid of the alignment dependence on timestamps, and SC-TS-ASR jointly trains target-speaker separation and ASR modules, which achieves the best performance.

Automatic Speech Recognition speaker-diarization +3

Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning

1 code implementation27 Oct 2022 Qiu-Shi Zhu, Long Zhou, Jie Zhang, Shu-Jie Liu, Yu-Chen Hu, Li-Rong Dai

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR).

Automatic Speech Recognition Contrastive Learning +3

Speech Enhancement Using Self-Supervised Pre-Trained Model and Vector Quantization

no code implementations28 Sep 2022 Xiao-Ying Zhao, Qiu-Shi Zhu, Jie Zhang

Specifically, the encoder and bottleneck layer of the DEMUCS model are initialized using the self-supervised pretrained WavLM model, the convolution in the encoder is replaced by causal convolution, and the transformer encoder in the bottleneck layer is based on causal attention mask.

Denoising Quantization +1

Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning

1 code implementation13 Sep 2022 Rongkai Zhang, Cong Zhang, Zhiguang Cao, Wen Song, Puay Siew Tan, Jie Zhang, Bihan Wen, Justin Dauwels

We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.

Class-Incremental Learning via Knowledge Amalgamation

1 code implementation5 Sep 2022 Marcus de Carvalho, Mahardhika Pratama, Jie Zhang, Yajuan San

Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting.

class-incremental learning Incremental Learning

A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals

1 code implementation1 Sep 2022 Zhu Sun, Yu Lei, Lu Zhang, Chen Li, Yew-Soon Ong, Jie Zhang

Being equipped with three modules (i. e., global user behavior encoder, local multi-channel encoder, and region-aware weighting strategy), MCMG is capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the region check-in patterns.

Federated Learning with Label Distribution Skew via Logits Calibration

1 code implementation1 Sep 2022 Jie Zhang, Zhiqi Li, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Chao Wu

Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.

Federated Learning

Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network

no code implementations21 Aug 2022 Jingcai Guo, Song Guo, Jie Zhang, Ziming Liu

Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model.

Federated Learning Privacy Preserving

Hierarchical Compositional Representations for Few-shot Action Recognition

no code implementations19 Aug 2022 Changzhen Li, Jie Zhang, Shuzhe Wu, Xin Jin, Shiguang Shan

Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction.

Few-Shot action recognition Few Shot Action Recognition

Multi-modal Transformer Path Prediction for Autonomous Vehicle

no code implementations15 Aug 2022 Chia Hong Tseng, Jie Zhang, Min-Te Sun, Kazuya Sakai, Wei-Shinn Ku

To better utilize the lane information, the lanes which are in opposite direction to target agent are not likely to be taken by the target agent and are consequently filtered out.

Autonomous Driving Trajectory Forecasting

Microwave QR Code: An IRS-Based Solution

no code implementations5 Aug 2022 Sai Xu, Yanan Du, Jiliang Zhang, Jie Zhang

This letter proposes to employ intelligent reflecting surface (IRS) as an information media to display a microwave quick response (QR) code for Internet-of-Things applications.

An IRS Backscatter Enabled Integrated Sensing, Communication and Computation System

no code implementations20 Jul 2022 Sai Xu, Yanan Du, Jiliang Zhang, Jiangzhou Wang, Jie Zhang

This paper proposes to leverage intelligent reflecting surface (IRS) backscatter to realize radio-frequency-chain-free uplink-transmissions (RFCF-UT).

On the Performance of Data Compression in Clustered Fog Radio Access Networks

no code implementations1 Jul 2022 Haonan Hu, Yan Jiang, Jiliang Zhang, Yanan Zheng, Qianbin Chen, Jie Zhang

The fog-radio-access-network (F-RAN) has been proposed to address the strict latency requirements, which offloads computation tasks generated in user equipments (UEs) to the edge to reduce the processing latency.

Data Compression

DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

2 code implementations22 Jun 2022 Zhu Sun, Hui Fang, Jie Yang, Xinghua Qu, Hongyang Liu, Di Yu, Yew-Soon Ong, Jie Zhang

Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.

Recommendation Systems

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

no code implementations20 Jun 2022 Wenhui Huang, Cong Zhang, Jingda Wu, Xiangkun He, Jie Zhang, Chen Lv

We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values.

Q-Learning reinforcement-learning +1

Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR

no code implementations26 May 2022 Qiu-Shi Zhu, Jie Zhang, Zi-Qiang Zhang, Li-Rong Dai

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion.

Automatic Speech Recognition Speech Enhancement +1

QEKD: Query-Efficient and Data-Free Knowledge Distillation from Black-box Models

no code implementations23 May 2022 Jie Zhang, Chen Chen, Jiahua Dong, Ruoxi Jia, Lingjuan Lyu

Knowledge distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model.

Knowledge Distillation

On Scheduling Mechanisms Beyond the Worst Case

no code implementations14 Apr 2022 Yansong Gao, Jie Zhang

That is, mechanism K is pointwise better than mechanism P. Next, for each task $j$, when machines' execution costs $t_i^j$ are independent and identically drawn from a task-specific distribution $F^j(t)$, we show that the average-case approximation ratio of mechanism K converges to a constant.


Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression

no code implementations14 Apr 2022 Feijie Wu, Shiqi He, Song Guo, Zhihao Qu, Haozhao Wang, Weihua Zhuang, Jie Zhang

Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.

Adaptive Modulation for Wobbling UAV Air-to-Ground Links in Millimeter-wave Bands

no code implementations13 Apr 2022 Songjiang Yang, Zitian Zhang, Jiliang Zhang, Xiaoli Chu, Jie Zhang

Based on the designed detectors, we propose an adaptive modulation scheme to maximize the average transmission rate under imperfect CSI by optimizing the data transmission time subject to the maximum tolerable BEP.

Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective

1 code implementation12 Apr 2022 Yitong Ji, Aixin Sun, Jie Zhang, Chenliang Li

Our study offers a different perspective to understand recommender accuracy, and our findings could trigger a revisit of recommender model design.

Recommendation Systems

PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems

1 code implementation11 Apr 2022 Yuanxing Zhang, Langshi Chen, Siran Yang, Man Yuan, Huimin Yi, Jie Zhang, Jiamang Wang, Jianbo Dong, Yunlong Xu, Yue Song, Yong Li, Di Zhang, Wei Lin, Lin Qu, Bo Zheng

However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.

Marketing Recommendation Systems

A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition

no code implementations5 Apr 2022 Ye-Qian Du, Jie Zhang, Qiu-Shi Zhu, Li-Rong Dai, Ming-Hui Wu, Xin Fang, Zhou-Wang Yang

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training.

Automatic Speech Recognition Language Modelling +1

Spectral Graph Clustering for Intentional Islanding Operations in Resilient Hybrid Energy Systems

no code implementations13 Mar 2022 Jiaxin Wu, Xin Chen, Sobhan Badakhshan, Jie Zhang, Pingfeng Wang

Establishing cleaner energy generation therefore improving the sustainability of the power system is a crucial task in this century, and one of the key strategies being pursued is to shift the dependence on fossil fuel to renewable technologies such as wind, solar, and nuclear.

Graph Clustering Spectral Graph Clustering

Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition

no code implementations15 Feb 2022 Zi-Qiang Zhang, Jie Zhang, Jian-Shu Zhang, Ming-Hui Wu, Xin Fang, Li-Rong Dai

The proposed approach explores both the complementarity of audio-visual modalities and long-term context dependency using a transformer-based fusion module and a flexible masking strategy.

Audio-Visual Speech Recognition Lipreading +4

Learning to Solve Routing Problems via Distributionally Robust Optimization

1 code implementation15 Feb 2022 Yuan Jiang, Yaoxin Wu, Zhiguang Cao, Jie Zhang

Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability.

A Coalition Formation Game Approach for Personalized Federated Learning

no code implementations5 Feb 2022 Leijie Wu, Song Guo, Yaohong Ding, Yufeng Zhan, Jie Zhang

Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot.

Personalized Federated Learning

Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning

1 code implementation28 Jan 2022 Jie Zhang, Lei Zhang, Gang Li, Chao Wu

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes.

Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals

no code implementations22 Jan 2022 Xing-Yu Chen, Qiu-Shi Zhu, Jie Zhang, Li-Rong Dai

By using the acoustic signals to train the network, respectively, we can build individual models for three tasks, whose parameters are averaged to obtain an average model, which is then used as the initialization for the BiLSTM model training of each task.

Enhancing Face Recognition With Self-Supervised 3D Reconstruction

no code implementations CVPR 2022 Mingjie He, Jie Zhang, Shiguang Shan, Xilin Chen

In this paper, we propose to enhance face recognition with a bypass of self-supervised 3D reconstruction, which enforces the neural backbone to focus on the identity-related depth and albedo information while neglects the identity-irrelevant pose and illumination information.

3D Face Reconstruction 3D Reconstruction +2

Towards Efficient Data Free Black-Box Adversarial Attack

1 code implementation CVPR 2022 Jie Zhang, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Lei Zhang, Chao Wu

The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.

Adversarial Attack

DENSE: Data-Free One-Shot Federated Learning

1 code implementation23 Dec 2021 Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, Chao Wu

One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.

Federated Learning

Initiative Defense against Facial Manipulation

no code implementations19 Dec 2021 Qidong Huang, Jie Zhang, Wenbo Zhou, WeimingZhang, Nenghai Yu

To this end, we first imitate the target manipulation model with a surrogate model, and then devise a poison perturbation generator to obtain the desired venom.

Face Reenactment

From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization

no code implementations17 Dec 2021 Feijie Wu, Song Guo, Haozhao Wang, Zhihao Qu, Haobo Zhang, Jie Zhang, Ziming Liu

In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training with fully utilizing their computational resources.

GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation

no code implementations16 Dec 2021 Jie Zhang, Ke-Jia Chen, Jingqiang Chen

Sequential recommendation based on multi-interest framework models the user's recent interaction sequence into multiple different interest vectors, since a single low-dimensional vector cannot fully represent the diversity of user interests.

Sequential Recommendation

Tracing Text Provenance via Context-Aware Lexical Substitution

no code implementations15 Dec 2021 Xi Yang, Jie Zhang, Kejiang Chen, Weiming Zhang, Zehua Ma, Feng Wang, Nenghai Yu

Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.

Optical Character Recognition

Deep Auto-encoder with Neural Response

no code implementations30 Nov 2021 Xuming Ran, Jie Zhang, Ziyuan Ye, Haiyan Wu, Qi Xu, Huihui Zhou, Quanying Liu

In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.

Image Reconstruction

Adaptive Image Transformations for Transfer-based Adversarial Attack

1 code implementation27 Nov 2021 Zheng Yuan, Jie Zhang, Shiguang Shan

Adversarial attacks provide a good way to study the robustness of deep learning models.

Adversarial Attack

Adaptive Perturbation for Adversarial Attack

no code implementations27 Nov 2021 Zheng Yuan, Jie Zhang, Zhaoyan Jiang, Liangliang Li, Shiguang Shan

Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations.

Adversarial Attack

3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions

no code implementations18 Nov 2021 Jie Zhang, Robert B. Fisher

We define a motion divergence measure using 3D lip landmarks to quantify the interframe dynamics of a 3D speaking lip.

Event Detection Motion Detection

Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

1 code implementation8 Nov 2021 Danni Peng, Sinno Jialin Pan, Jie Zhang, AnXiang Zeng

Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily.

Recommendation Systems

Parameterized Knowledge Transfer for Personalized Federated Learning

1 code implementation NeurIPS 2021 Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wencao Xu, Feijie Wu

To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.

Personalized Federated Learning Transfer Learning

Learning Large Neighborhood Search Policy for Integer Programming

1 code implementation NeurIPS 2021 Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang

We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm.

A Novel Sequence Tagging Framework for Consumer Event-Cause Extraction

no code implementations28 Oct 2021 Congqing He, Jie Zhang, Xiangyu Zhu, Huan Liu, Yukun Huang

To this end, we introduce a fresh perspective to revisit the relational event-cause extraction task and propose a novel sequence tagging framework, instead of extracting event types and events-causes separately.

SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing

no code implementations24 Oct 2021 Kafeng Wang, Haoyi Xiong, Jie Zhang, Hongyang Chen, Dejing Dou, Cheng-Zhong Xu

Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).


Cross-Vendor CT Image Data Harmonization Using CVH-CT

no code implementations19 Oct 2021 Md Selim, Jie Zhang, Baowei Fei, Guo-Qiang Zhang, Gary Yeeming Ge, Jin Chen

We propose a novel deep learning approach called CVH-CT for harmonizing CT images captured using scanners from different vendors.

Computed Tomography (CT)

NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem

1 code implementation NeurIPS 2021 Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem.

Traveling Salesman Problem

M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining

no code implementations8 Oct 2021 Junyang Lin, An Yang, Jinze Bai, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Yong Li, Wei Lin, Jingren Zhou, Hongxia Yang

Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

1 code implementation6 Oct 2021 Jingwen Li, Yining Ma, Ruize Gao, Zhiguang Cao, Andrew Lim, Wen Song, Jie Zhang

To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step.

reinforcement-learning reinforcement Learning

Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning

no code implementations6 Oct 2021 Jingwen Li, Liang Xin, Zhiguang Cao, Andrew Lim, Wen Song, Jie Zhang

In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i. e., the pickup node must precede the pairing delivery node.

reinforcement-learning reinforcement Learning

ACDC: Online Unsupervised Cross-Domain Adaptation

1 code implementation4 Oct 2021 Marcus de Carvalho, Mahardhika Pratama, Jie Zhang, Edward Yapp

We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.

Online unsupervised domain adaptation

Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs

no code implementations ICLR 2022 Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang

Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity.

Combinatorial Optimization

Generative Adversarial Training for Neural Combinatorial Optimization Models

no code implementations29 Sep 2021 Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Recent studies show that deep neural networks can be trained to learn good heuristics for various Combinatorial Optimization Problems (COPs).

Combinatorial Optimization Traveling Salesman Problem

Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark

1 code implementation23 Sep 2021 Xun Gao, Yin Zhao, Jie Zhang, Longjun Cai

We expect the ERATO as well as our proposed SMTA to open up a new way for PERR task in video understanding and further improve the research of multi-modal fusion methodology.

Video Understanding

Exploring Structure Consistency for Deep Model Watermarking

no code implementations5 Aug 2021 Jie Zhang, Dongdong Chen, Jing Liao, Han Fang, Zehua Ma, Weiming Zhang, Gang Hua, Nenghai Yu

However, little attention has been devoted to the protection of DNNs in image processing tasks.

Data Augmentation

Poison Ink: Robust and Invisible Backdoor Attack

1 code implementation5 Aug 2021 Jie Zhang, Dongdong Chen, Qidong Huang, Jing Liao, Weiming Zhang, Huamin Feng, Gang Hua, Nenghai Yu

As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations.

Backdoor Attack Data Poisoning

Locality-aware Channel-wise Dropout for Occluded Face Recognition

no code implementations20 Jul 2021 Mingjie He, Jie Zhang, Shiguang Shan, Xiao Liu, Zhongqin Wu, Xilin Chen

Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.

Face Recognition

Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems

no code implementations19 Jul 2021 Jie Zhang, Alexandra Brintrup, Anisoara Calinescu, Edward Kosasih, Angira Sharma

This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue.

Impact of Rotary-Wing UAV Wobbling on Millimeter-wave Air-to-Ground Wireless Channel

no code implementations14 Jul 2021 Songjiang Yang, Zitian Zhang, Jiliang Zhang, Jie Zhang

Our contributions of this paper lie in: i) modeling the wobbling process of a hovering RW UAV; ii) developing an analytical model to derive the channel temporal autocorrelation function (ACF) for the millimeter-wave RW UAV A2G link in a closed-form expression; and iii) investigating how RW UAV wobbling impacts the Doppler effect on the millimeter-wave RW UAV A2G link.

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

2 code implementations7 Jul 2021 Xin Zhou, Aixin Sun, Yong liu, Jie Zhang, Chunyan Miao

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.

Collaborative Filtering Self-Supervised Learning

CT Image Harmonization for Enhancing Radiomics Studies

no code implementations3 Jul 2021 Md Selim, Jie Zhang, Baowei Fei, Guo-Qiang Zhang, Jin Chen

While remarkable advances have been made in Computed Tomography (CT), capturing CT images with non-standardized protocols causes low reproducibility regarding radiomic features, forming a barrier on CT image analysis in a large scale.

Computed Tomography (CT) Image Harmonization

From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques

no code implementations2 Jul 2021 Zhiyuan Wang, Haoyi Xiong, Jie Zhang, Sijia Yang, Mehdi Boukhechba, Laura E. Barnes, Daqing Zhang, Dejing Dou

Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.

M6-T: Exploring Sparse Expert Models and Beyond

no code implementations31 May 2021 An Yang, Junyang Lin, Rui Men, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Jiamang Wang, Yong Li, Di Zhang, Wei Lin, Lin Qu, Jingren Zhou, Hongxia Yang

Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.


HINet: Half Instance Normalization Network for Image Restoration

2 code implementations13 May 2021 Liangyu Chen, Xin Lu, Jie Zhang, Xiaojie Chu, Chengpeng Chen

Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.

Deblurring Image Deblurring +3

Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication

no code implementations9 Apr 2021 Xiquan Guan, Huamin Feng, Weiming Zhang, Hang Zhou, Jie Zhang, Nenghai Yu

Specifically, we present the reversible watermarking problem of deep convolutional neural networks and utilize the pruning theory of model compression technology to construct a host sequence used for embedding watermarking information by histogram shift.

Model Compression

Deep Model Intellectual Property Protection via Deep Watermarking

1 code implementation8 Mar 2021 Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Huamin Feng, Gang Hua, Nenghai Yu

By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model.

M6: A Chinese Multimodal Pretrainer

no code implementations1 Mar 2021 Junyang Lin, Rui Men, An Yang, Chang Zhou, Ming Ding, Yichang Zhang, Peng Wang, Ang Wang, Le Jiang, Xianyan Jia, Jie Zhang, Jianwei Zhang, Xu Zou, Zhikang Li, Xiaodong Deng, Jie Liu, Jinbao Xue, Huiling Zhou, Jianxin Ma, Jin Yu, Yong Li, Wei Lin, Jingren Zhou, Jie Tang, Hongxia Yang

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.

Image Generation

Dynamic Virtual Graph Significance Networks for Predicting Influenza

1 code implementation16 Feb 2021 Jie Zhang, Pengfei Zhou, Hongyan Wu

In this study, we develop a novel method, Dynamic Virtual Graph Significance Networks (DVGSN), which can supervisedly and dynamically learn from similar "infection situations" in historical timepoints.

Representation Learning Time Series Prediction

Meta-Path-Free Representation Learning on Heterogeneous Networks

no code implementations16 Feb 2021 Jie Zhang, Jinru Ding, Suyuan Liu, Hongyan Wu

To the best of our knowledge, this is the first attempt to break out of the confinement of meta-paths for representation learning on heterogeneous networks.

Knowledge Graphs Representation Learning

Spatio-Temporal Multi-step Prediction of Influenza Outbreaks

no code implementations16 Feb 2021 Jie Zhang, Kazumitsu Nawata, Hongyan Wu

We compared the MAPEs of SVM, RF, LSTM models of predicting flu data of the 1-4 weeks ahead with and without other countries' flu data.

Spin and polarization effects on the nonlinear Breit-Wheeler pair production in laser-plasma interaction

no code implementations11 Feb 2021 Huai-Hang Song, Wei-Min Wang, Yan-Fei Li, Bing-Jun Li, Yu-Tong Li, Zheng-Ming Sheng, Li-Ming Chen, Jie Zhang

The spin effect of electrons/positrons ($e^-$/$e^+$) and polarization effect of $\gamma$ photons are investigated in the interaction of two counter-propagating linearly polarized 10-PW-class laser pulses with a thin foil target.

Plasma Physics

An Improvement for Quantum Tunneling Radiation of Fermions in a Stationary Kerr-Newman Black Hole Spacetime

no code implementations9 Feb 2021 Jie Zhang, Menquan Liu, Zhie Liu, Shuzheng Yang

By introducing a specific etheric-like vector in the Dirac equation with Lorentz Invariance Violation (LIV) in the curved spacetime, an improved method for quantum tunneling radiation of fermions is proposed.

General Relativity and Quantum Cosmology High Energy Physics - Theory

BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactions

1 code implementation29 Jan 2021 Yifan Wu, Min Gao, Min Zeng, Feiyang Chen, Min Li, Jie Zhang

Therefore, we hope to develop a novel supervised learning method to learn the PPAs and DDAs effectively and thereby improve the prediction performance of the specific task of DPI.

Drug Discovery

Optical manipulation of electronic dimensionality in a quantum material

no code implementations21 Jan 2021 Shaofeng Duan, Yun Cheng, Wei Xia, Yuanyuan Yang, Fengfeng Qi, Tianwei Tang, Yanfeng Guo, Dong Qian, Dao Xiang, Jie Zhang, Wentao Zhang

Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions.

Strongly Correlated Electrons Materials Science Superconductivity

Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning

no code implementations23 Dec 2020 Andreanne Lemay, Charley Gros, Zhizheng Zhuo, Jie Zhang, Yunyun Duan, Julien Cohen-Adad, Yaou Liu

To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation.

Tumor Segmentation

Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems

1 code implementation19 Dec 2020 Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems.

reinforcement-learning reinforcement Learning

Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction

no code implementations24 Nov 2020 Yanshi Wang, Jie Zhang, Qing Da, AnXiang Zeng

In this paper, we propose a novel neural network framework ESDF to tackle the above three challenges simultaneously.

Selection bias Survival Analysis

Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions

no code implementations2 Nov 2020 Angira Sharma, Edward Kosasih, Jie Zhang, Alexandra Brintrup, Anisoara Calinescu

This work explores the various DT features and current approaches, the shortcomings and reasons behind the delay in the implementation and adoption of digital twin.

Passport-aware Normalization for Deep Model Protection

1 code implementation NeurIPS 2020 Jie Zhang, Dongdong Chen, Jing Liao, Weiming Zhang, Gang Hua, Nenghai Yu

Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification.

Model Compression

A Critical Study on Data Leakage in Recommender System Offline Evaluation

1 code implementation21 Oct 2020 Yitong Ji, Aixin Sun, Jie Zhang, Chenliang Li

To evaluate recommendation systems in a realistic manner in offline setting, we propose a timeline scheme, which calls for a revisit of the recommendation model design.

Collaborative Filtering Recommendation Systems

Low-frequency whistler waves excited by relativistic laser pulses

no code implementations15 Oct 2020 Huai-Hang Song, Wei-Min Wang, Jia-Qi Wang, Yu-Tong Li, Jie Zhang

It is shown by multi-dimensional particle-in-cell simulations that intense secondary whistler waves with special vortex-like field topology can be excited by a relativistic laser pulse in the highly magnetized, near-critical density plasma.

Plasma Physics

Cascaded Semantic and Positional Self-Attention Network for Document Classification

no code implementations Findings of the Association for Computational Linguistics 2020 Juyong Jiang, Jie Zhang, Kai Zhang

In this work, we propose a new architecture to aggregate the two sources of information using cascaded semantic and positional self-attention network (CSPAN) in the context of document classification.

Classification Document Classification +2

Low-Rank Reorganization via Proportional Hazards Non-negative Matrix Factorization Unveils Survival Associated Gene Clusters

no code implementations9 Aug 2020 Zhi Huang, Paul Salama, Wei Shao, Jie Zhang, Kun Huang

Towards the goal of precision health and cancer treatments, the proposed algorithm can help understand and interpret high-dimensional heterogeneous genomics data with accurate identification of survival-associated gene clusters.


FrUITeR: A Framework for Evaluating UI Test Reuse

no code implementations8 Aug 2020 Yixue Zhao, Justin Chen, Adriana Sejfia, Marcelo Schmitt Laser, Jie Zhang, Federica Sarro, Mark Harman, Nenad Medvidovic

UI testing is tedious and time-consuming due to the manual effort required.

Software Engineering

Wireless Performance Evaluation of Building Layouts: Closed-Form Computation of Figures of Merit

no code implementations20 Jul 2020 Jiliang Zhang, Andrés Alayón Glazunov, Jie Zhang

This paper presents a part of our ground-breaking work on evaluation of buildings in terms of wireless friendliness in the building-design stage.

Federated Mutual Learning

1 code implementation27 Jun 2020 Tao Shen, Jie Zhang, Xinkang Jia, Fengda Zhang, Gang Huang, Pan Zhou, Kun Kuang, Fei Wu, Chao Wu

The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.

Federated Learning

Active Sampling for Min-Max Fairness

1 code implementation11 Jun 2020 Jacob Abernethy, Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern, Chris Russell, Jie Zhang

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization.

Fairness regression

A Re-visit of the Popularity Baseline in Recommender Systems

1 code implementation28 May 2020 Yitong Ji, Aixin Sun, Jie Zhang, Chenliang Li

On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system.

Recommendation Systems

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

no code implementations22 May 2020 Jia-Wei Chen, Rongfang Wang, Fan Ding, Bo Liu, Licheng Jiao, Jie Zhang

Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset.

Change Detection

Benchmarking High Bandwidth Memory on FPGAs

2 code implementations9 May 2020 Zeke Wang, Hongjing Huang, Jie Zhang, Gustavo Alonso

FPGAs are starting to be enhanced with High Bandwidth Memory (HBM) as a way to reduce the memory bandwidth bottleneck encountered in some applications and to give the FPGA more capacity to deal with application state.

Hardware Architecture

Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling

no code implementations8 May 2020 Manchao Zhang, Yi Xie, Jie Zhang, Weichen Wang, Chunwang Wu, Ting Chen, Wei Wu, Pingxing Chen

Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.

Quantum Physics

Adaptive Structural Fingerprints for Graph Attention Networks

no code implementations ICLR 2020 Kai Zhang, Yaokang Zhu, Jun Wang, Jie Zhang

Yet, how to fully exploit rich structural information in the attention mechanism remains a challenge.

Graph Attention

Single-Side Domain Generalization for Face Anti-Spoofing

1 code implementation CVPR 2020 Yunpei Jia, Jie Zhang, Shiguang Shan, Xilin Chen

In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing.

Domain Generalization Face Anti-Spoofing

Reconstructing normal section profiles of 3D revolving structures via pose-unconstrained multi-line structured-light vision

no code implementations27 Apr 2020 Junhua Sun, Zhou Zhang, Jie Zhang

First, we establish a model to estimate the axis of 3D revolving geometrical structure and the normal section profile using corresponding points.

Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation

2 code implementations CVPR 2020 Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen

Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation.

Data Augmentation Weakly supervised Semantic Segmentation +1

STAN-CT: Standardizing CT Image using Generative Adversarial Network

1 code implementation2 Apr 2020 Md. Selim, Jie Zhang, Baowei Fei, Guo-Qiang Zhang, Jin Chen

Computed tomography (CT) plays an important role in lung malignancy diagnostics and therapy assessment and facilitating precision medicine delivery.

Computed Tomography (CT)

Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images

no code implementations1 Apr 2020 Rui Nie, Huan Yang, Hejuan Peng, Wenbin Luo, Weiya Fan, Jie Zhang, Jing Liao, Fang Huang, Yufeng Xiao

Small intestinal capsule endoscopy is the mainstream method for inspecting small intestinal lesions, but a single small intestinal capsule endoscopy will produce 60, 000 - 120, 000 images, the majority of which are similar and have no diagnostic value.

Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character

no code implementations28 Mar 2020 Fenxi Xiao, Jie Zhang, Bo Huang, Xia Wu

The main purpose of this paper is to design a network framework that can extract and recombine the content and style of the characters.

Style Transfer Translation

Model Watermarking for Image Processing Networks

1 code implementation25 Feb 2020 Jie Zhang, Dong-Dong Chen, Jing Liao, Han Fang, Weiming Zhang, Wenbo Zhou, HAO CUI, Nenghai Yu

In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.

Bounded Incentives in Manipulating the Probabilistic Serial Rule

no code implementations28 Jan 2020 Zihe Wang, Zhide Wei, Jie Zhang

In this paper, we characterize the extent to which an individual agent can increase its utility by strategic manipulation.


Learning Variable Ordering Heuristics for Solving Constraint Satisfaction Problems

1 code implementation23 Dec 2019 Wen Song, Zhiguang Cao, Jie Zhang, Andrew Lim

In this paper, we propose a deep reinforcement learning based approach to automatically discover new variable ordering heuristics that are better adapted for a given class of CSP instances.

COBRA: Context-aware Bernoulli Neural Networks for Reputation Assessment

no code implementations18 Dec 2019 Leonit Zeynalvand, Tie Luo, Jie Zhang

Trust and reputation management (TRM) plays an increasingly important role in large-scale online environments such as multi-agent systems (MAS) and the Internet of Things (IoT).

BIG-bench Machine Learning Management

Learning Improvement Heuristics for Solving Routing Problems

1 code implementation12 Dec 2019 Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Andrew Lim

In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems.

Which Channel to Ask My Question? Personalized Customer Service RequestStream Routing using DeepReinforcement Learning

no code implementations24 Nov 2019 Zining Liu, Chong Long, Xiaolu Lu, Zehong Hu, Jie Zhang, Yafang Wang

These observations suggest that our proposed method can seek the trade-off where both channel resources and customers' satisfaction are optimal.

Chatbot Q-Learning +2

Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal

no code implementations18 Oct 2019 Jie Zhang, Yuping Duan, Yue Lu, Michael K. Ng, Huibin Chang

In this paper, we propose new operator-splitting algorithms for the total variation regularized infimal convolution (TV-IC) model [4] in order to remove mixed Poisson-Gaussian(MPG) noise.

Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation

no code implementations18 Oct 2019 Xiao Sha, Zhu Sun, Jie Zhang

Knowledge graphs (KGs) have proven to be effective for high-quality recommendation, where the connectivities between users and items provide rich and complementary information to user-item interactions.

Knowledge Graph Embedding Knowledge Graphs

Diagonal Graph Convolutional Networks with Adaptive Neighborhood Aggregation

no code implementations25 Sep 2019 Jie Zhang, Yuxiao Dong, Jie Tang

In this paper, we revisit the mathematical foundation of GCNs and study how to extend their representation capacity.

Graph Attention Graph Classification +1


no code implementations25 Sep 2019 Yin Zhao, Longjun Cai, Chaoping Tu, Jie Zhang, Wu Wei

Feature extraction, multi-modal fusion and temporal context fusion are crucial stages for predicting valence and arousal values in the emotional impact, but have not been successfully exploited.

Research Commentary on Recommendations with Side Information: A Survey and Research Directions

no code implementations19 Sep 2019 Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke

This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.

Knowledge Graphs Recommendation Systems +1

Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context

no code implementations1 Sep 2019 Jie Zhang, Yin Zhao, Longjun Cai, Chaoping Tu, Wu Wei

We select the most suitable modalities for valence and arousal tasks respectively and each modal feature is extracted using the modality-specific pre-trained deep model on large generic dataset.

FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images

no code implementations28 Jul 2019 Yunhe Gao, Rui Huang, Ming Chen, Zhe Wang, Jincheng Deng, YuanYuan Chen, Yiwei Yang, Jie Zhang, Chanjuan Tao, Hongsheng Li

In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.

Method of diagnosing heart disease based on deep learning ECG signal

no code implementations25 Jun 2019 Jie Zhang, Bohao Li, Kexin Xiang, Xuegang Shi

Some have tried to combine expertise and signal processing to classify ECG signal by heart disease type.

Transferrable Operative Difficulty Assessment in Robot-assisted Teleoperation: A Domain Adaptation Approach

no code implementations12 Jun 2019 Ziheng Wang, Cong Feng, Jie Zhang, Ann Majewicz Fey

Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operators to use.

Steering Control Unsupervised Domain Adaptation

Average-case Analysis of the Assignment Problem with Independent Preferences

no code implementations1 Jun 2019 Yansong Gao, Jie Zhang

Recently, [Deng, Gao, Zhang 2017] show that when the agents' preferences are drawn from a uniform distribution, its \textit{average-case approximation ratio} is upper bounded by 3. 718.

Multi-Normal Estimation via Pair Consistency Voting

1 code implementation1 Apr 2019 Jie Zhang, Junjie Cao, Xiuping Liu, He Chen, Bo Li, Ligang Liu

This paper presents a unified definition for point cloud normals of feature and non-feature points, which allows feature points to possess multiple normals.

Surface Normals Estimation from Point Clouds

Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML

no code implementations20 Mar 2019 Jie Zhang, Junting Zhang, Shalini Ghosh, Dawei Li, Jingwen Zhu, Heming Zhang, Yalin Wang

Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community.

AutoML Continual Learning

Class-incremental Learning via Deep Model Consolidation

2 code implementations19 Mar 2019 Junting Zhang, Jie Zhang, Shalini Ghosh, Dawei Li, Serafettin Tasci, Larry Heck, Heming Zhang, C. -C. Jay Kuo

The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.

class-incremental learning Image Classification +3

Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation

no code implementations26 Feb 2019 Heming Zhang, Shalini Ghosh, Larry Heck, Stephen Walsh, Junting Zhang, Jie Zhang, C. -C. Jay Kuo

The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow.

Visual Dialog

MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression

no code implementations3 Feb 2019 Jie Zhang, Xiaolong Wang, Dawei Li, Shalini Ghosh, Abhishek Kolagunda, Yalin Wang

State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer.

Knowledge Distillation Model Compression

Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection

no code implementations ECCV 2018 Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan

The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance.

Boundary Detection Lane Detection

Semi-supervised Learning on Graphs with Generative Adversarial Nets

1 code implementation1 Sep 2018 Ming Ding, Jie Tang, Jie Zhang

We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs.

An Operation Network for Abstractive Sentence Compression

no code implementations COLING 2018 Naitong Yu, Jie Zhang, Minlie Huang, Xiaoyan Zhu

Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression.

Sentence Compression Text Generation

Spectral Network Embedding: A Fast and Scalable Method via Sparsity

1 code implementation7 Jun 2018 Jie Zhang, Yan Wang, Jie Tang, Ming Ding

In this paper, we propose a $10\times \sim 100\times$ faster network embedding method, called Progle, by elegantly utilizing the sparsity property of online networks and spectral analysis.

Link Prediction Network Embedding +1

Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing

no code implementations NeurIPS 2018 Zehong Hu, Yitao Liang, Yang Liu, Jie Zhang

Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels.

Bayesian Inference reinforcement-learning +1

Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending

no code implementations9 Mar 2018 Cong Feng, Jie Zhang

The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour.

BIG-bench Machine Learning

Interacting Attention-gated Recurrent Networks for Recommendation

no code implementations5 Sep 2017 Wenjie Pei, Jie Yang, Zhu Sun, Jie Zhang, Alessandro Bozzon, David M. J. Tax

In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions.

Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images

no code implementations31 Aug 2017 Jie Zhang, Qingyang Li, Richard J. Caselli, Jieping Ye, Yalin Wang

Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks.

Dictionary Learning Image Classification +1

Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction

no code implementations6 Aug 2017 Jie Zhang, Christos Maniatis, Luis Horna, Robert B. Fisher

The availability of high-speed 3D video sensors has greatly facilitated 3D shape acquisition of dynamic and deformable objects, but high frame rate 3D reconstruction is always degraded by spatial noise and temporal fluctuations.

3D Reconstruction

Seeing the Forest from the Trees in Two Looks: Matrix Sketching by Cascaded Bilateral Sampling

no code implementations25 Jul 2016 Kai Zhang, Chuanren Liu, Jie Zhang, Hui Xiong, Eric Xing, Jieping Ye

Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition.

Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders

no code implementations CVPR 2016 Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen

Face alignment or facial landmark detection plays an important role in many computer vision applications, e. g., face recognition, facial expression recognition, face animation, etc.

Face Alignment Face Recognition +3

Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network

no code implementations ICCV 2015 Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen

Facial landmark detection, as a vital topic in computer vision, has been studied for many decades and lots of datasets have been collected for evaluation.

Face Alignment Facial Landmark Detection +1

Scaling POMDPs For Selecting Sellers in E-markets-Extended Version

no code implementations30 Nov 2015 Athirai A. Irissappane, Frans A. Oliehoek, Jie Zhang

In multiagent e-marketplaces, buying agents need to select good sellers by querying other buyers (called advisors).

Correlative Multi-Label Multi-Instance Image Annotation

no code implementations IEEE International Conference on Computer Vision 2011 Xiangyang Xue, Wei zhang, Jie Zhang, Bin Wu, Jianping Fan, Yao Lu

The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.