Search Results for author: Tao Zhang

Found 128 papers, 31 papers with code

M3D-VTON: A Monocular-to-3D Virtual Try-On Network

1 code implementation ICCV 2021 Fuwei Zhao, Zhenyu Xie, Michael Kampffmeyer, Haoye Dong, Songfang Han, Tianxiang Zheng, Tao Zhang, Xiaodan Liang

Virtual 3D try-on can provide an intuitive and realistic view for online shopping and has a huge potential commercial value.

Virtual Try-on

DVIS: Decoupled Video Instance Segmentation Framework

1 code implementation ICCV 2023 Tao Zhang, Xingye Tian, Yu Wu, Shunping Ji, Xuebo Wang, Yuan Zhang, Pengfei Wan

The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement.

Autonomous Driving Instance Segmentation +5

1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation

1 code implementation7 Jun 2023 Tao Zhang, Xingye Tian, Haoran Wei, Yu Wu, Shunping Ji, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan

In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation.

Autonomous Driving Segmentation +2

1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation

1 code implementation28 Aug 2023 Tao Zhang, Xingye Tian, Yikang Zhou, Yu Wu, Shunping Ji, Cilin Yan, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan

Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving.

Autonomous Driving Denoising +6

DVIS++: Improved Decoupled Framework for Universal Video Segmentation

1 code implementation20 Dec 2023 Tao Zhang, Xingye Tian, Yikang Zhou, Shunping Ji, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Yu Wu

We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS).

Contrastive Learning Denoising +6

Point Could Mamba: Point Cloud Learning via State Space Model

1 code implementation1 Mar 2024 Tao Zhang, Xiangtai Li, Haobo Yuan, Shunping Ji, Shuicheng Yan

To enable more effective processing of 3-D point cloud data by Mamba, we propose a novel Consistent Traverse Serialization to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent.

A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling

1 code implementation17 Oct 2022 Ye Wang, Xinxin Liu, Wenxin Hu, Tao Zhang

To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning.

Document-level RE with incomplete labeling

Modeling Two-Way Selection Preference for Person-Job Fit

1 code implementation18 Aug 2022 Chen Yang, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen, Wayne Xin Zhao

To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph.

Contrastive Learning Graph Representation Learning +1

Hyperspectral Image Denoising With Realistic Data

1 code implementation ICCV 2021 Tao Zhang, Ying Fu, Cheng Li

On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.

Hyperspectral Image Denoising Image Denoising

FC$^2$N: Fully Channel-Concatenated Network for Single Image Super-Resolution

1 code implementation7 Jul 2019 Xiaole Zhao, Ying Liao, Tian He, Yulun Zhang, Yadong Wu, Tao Zhang

Most current image super-resolution (SR) methods based on convolutional neural networks (CNNs) use residual learning in network structural design, which favors to effective back propagation and hence improves SR performance by increasing model scale.

Image Super-Resolution

Compositional Generative Inverse Design

1 code implementation24 Jan 2024 Tailin Wu, Takashi Maruyama, Long Wei, Tao Zhang, Yilun Du, Gianluca Iaccarino, Jure Leskovec

In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes that are more complex than those in the training data.

CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping

1 code implementation CVPR 2022 Jilan Xu, Junlin Hou, Yuejie Zhang, Rui Feng, Rui-Wei Zhao, Tao Zhang, Xuequan Lu, Shang Gao

In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background.

Clustering Object +1

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

1 code implementation IJCNLP 2019 Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang song, Tao Zhang

Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.

Ranked #3 on Link Prediction on FB15k (MR metric)

Link Prediction Relation +1

PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images

1 code implementation13 Dec 2023 Tao Zhang, Kun Ding, Jinyong Wen, Yu Xiong, Zeyu Zhang, Shiming Xiang, Chunhong Pan

Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features.

Self-Supervised Learning

Multimodal Multi-objective Optimization: Comparative Study of the State-of-the-Art

1 code implementation11 Jul 2022 Wenhua Li, Tao Zhang, Rui Wang, Jing Liang

Multimodal multi-objective problems (MMOPs) commonly arise in real-world problems where distant solutions in decision space correspond to very similar objective values.

Evolutionary Algorithms

Adaptive Trajectory Estimation with Power Limited Steering Model under Perturbation Compensation

1 code implementation8 Dec 2019 Weipeng Li, Xiaogang Yang, Ruitao Lu, Jiwei Fan, Tao Zhang, Chuan He

The experiment of trajectory estimation demonstrates the convergence of AdaTE, and the better robust to the biased prior statistics and the observation drift compared with EKF, UKF and sparse MAP.

Information Theory Robotics Systems and Control Systems and Control Information Theory G.3.13; J.2.7

Coevolutionary Framework for Generalized Multimodal Multi-objective Optimization

1 code implementation2 Dec 2022 Wenhua Li, Xingyi Yao, Kaiwen Li, Rui Wang, Tao Zhang, Ling Wang

To address the above two issues, in this study, a novel coevolutionary framework termed CoMMEA for multimodal multi-objective optimization is proposed to better obtain both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs.

Evolutionary Algorithms Transfer Learning

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks

1 code implementation23 Oct 2023 Hoang H. Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, Philip S. Yu

While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.

Natural Language Understanding

Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

1 code implementation5 Mar 2021 Mengting Xu, Tao Zhang, Zhongnian Li, Mingxia Liu, Daoqiang Zhang

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images.

Adversarial Attack Multi-Label Classification

FedProc: Prototypical Contrastive Federated Learning on Non-IID data

1 code implementation25 Sep 2021 Xutong Mu, Yulong Shen, Ke Cheng, Xueli Geng, Jiaxuan Fu, Tao Zhang, Zhiwei Zhang

In this paper, we propose FedProc: prototypical contrastive federated learning, which is a simple and effective federated learning framework.

Federated Learning Image Classification

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network

1 code implementation28 Jun 2019 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks.

Enhancing Cross-lingual Transfer via Phonemic Transcription Integration

1 code implementation10 Jul 2023 Hoang H. Nguyen, Chenwei Zhang, Tao Zhang, Eugene Rohrbaugh, Philip S. Yu

Particularly, we propose unsupervised alignment objectives to capture (1) local one-to-one alignment between the two different modalities, (2) alignment via multi-modality contexts to leverage information from additional modalities, and (3) alignment via multilingual contexts where additional bilingual dictionaries are incorporated.

Cross-Lingual Transfer named-entity-recognition +3

JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction

1 code implementation7 Nov 2023 Zhongfen Deng, Hao Peng, Tao Zhang, Shuaiqi Liu, Wenting Zhao, Yibo Wang, Philip S. Yu

Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text.

Attribute Attribute Value Extraction +4

Kernel Relative-prototype Spectral Filtering for Few-shot Learning

1 code implementation24 Jul 2022 Tao Zhang, Wu Huang

In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS).

Few-Shot Learning

Deep Smart Contract Intent Detection

1 code implementation19 Nov 2022 Youwei Huang, Tao Zhang, Sen Fang, Youshuai Tan

Nowadays, security activities in smart contracts concentrate on vulnerability detection.

Intent Detection Multi-Label Classification +2

A Survey of Model Compression and Acceleration for Deep Neural Networks

no code implementations23 Oct 2017 Yu Cheng, Duo Wang, Pan Zhou, Tao Zhang

Methods of parameter pruning and quantization are described first, after that the other techniques are introduced.

Benchmarking Knowledge Distillation +2

A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning

1 code implementation22 Jun 2017 Jingjia Huang, Nannan Li, Tao Zhang, Ge Li

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.

Action Detection Position +2

Bootstrapping Face Detection with Hard Negative Examples

no code implementations7 Aug 2016 Shaohua Wan, Zhijun Chen, Tao Zhang, Bo Zhang, Kong-kat Wong

Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks.

Face Detection

Simulating user learning in authoritative technology adoption: An agent based model for council-led smart meter deployment planning in the UK

no code implementations20 Jul 2016 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper we investigate user learning in authoritative technology adoption by developing an agent-based model using the case of council-led smart meter deployment in the UK City of Leeds.

Management

Modelling Office Energy Consumption: An Agent Based Approach

no code implementations20 Jul 2016 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, based on a case study, to simulate the energy consumption in office buildings.

energy management Management

Dynamic Privacy For Distributed Machine Learning Over Network

no code implementations14 Jan 2016 Tao Zhang, Quanyan Zhu

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data.

BIG-bench Machine Learning Privacy Preserving

Modelling Electricity Consumption in Office Buildings: An Agent Based Approach

no code implementations31 May 2013 Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper, we develop an agent-based model which integrates four important elements, i. e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, to simulate the electricity consumption in office buildings.

energy management Management

Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector

no code implementations9 Jul 2018 Jia-Xing Zhong, Nannan Li, Weijie Kong, Tao Zhang, Thomas H. Li, Ge Li

Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data.

Action Detection Temporal Localization

Convolutional Neural Networks based Intra Prediction for HEVC

no code implementations17 Aug 2018 Wenxue Cui, Tao Zhang, Shengping Zhang, Feng Jiang, WangMeng Zuo, Debin Zhao

To overcome this problem, in this paper, an intra prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting the current block.

Channel Splitting Network for Single MR Image Super-Resolution

no code implementations15 Oct 2018 Xiaole Zhao, Yulun Zhang, Tao Zhang, Xueming Zou

The proposed CSN model divides the hierarchical features into two branches, i. e., residual branch and dense branch, with different information transmissions.

Image Super-Resolution

Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery

no code implementations ECCV 2018 Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang

Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).

Single MR Image Super-Resolution via Channel Splitting and Serial Fusion Network

no code implementations19 Jan 2019 Zhao Xiaole, Huali Zhang, Hangfei Liu, Yun Qin, Tao Zhang, Xueming Zou

Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images.

Image Super-Resolution

Acceleration of the NVT-flash calculation for multicomponent mixtures using deep neural network models

no code implementations27 Jan 2019 Yiteng Li, Tao Zhang, Shuyu Sun

Phase equilibrium calculation, also known as flash calculation, has been extensively applied in petroleum engineering, not only as a standalone application for separation process but also an integral component of compositional reservoir simulation.

SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction

no code implementations18 Feb 2019 Zhongnian Li, Tao Zhang, Peng Wan, Daoqiang Zhang

Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI).

Generative Adversarial Network MRI Reconstruction

Imbalanced Sentiment Classification Enhanced with Discourse Marker

no code implementations28 Mar 2019 Tao Zhang, Xing Wu, Meng Lin, Jizhong Han, Songlin Hu

Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.

Classification Data Augmentation +3

A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning

no code implementations4 Apr 2019 Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo, Tao Zhang

The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes.

Few-Shot Learning General Classification +3

Deep Reinforcement Learning for Multi-objective Optimization

no code implementations6 Jun 2019 Kaiwen Li, Tao Zhang, Rui Wang

The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time.

reinforcement-learning Reinforcement Learning (RL)

Data-Driven Machine Learning Techniques for Self-healing in Cellular Wireless Networks: Challenges and Solutions

no code implementations14 Jun 2019 Tao Zhang, Kun Zhu, Ekram Hossain

As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation.

BIG-bench Machine Learning Fault Detection +1

Hyperspectral Image Reconstruction Using Deep External and Internal Learning

no code implementations ICCV 2019 Tao Zhang, Ying Fu, Lizhi Wang, Hua Huang

To solve the low spatial and/or temporal resolution problem which the conventional hypelrspectral cameras often suffer from, coded snapshot hyperspectral imaging systems have attracted more attention recently.

Image Reconstruction

Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network

no code implementations IJCNLP 2019 Shuqing Bian, Wayne Xin Zhao, Yang song, Tao Zhang, Ji-Rong Wen

Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.

Domain Adaptation Sentence

DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks

no code implementations19 Nov 2019 Ao Ren, Tao Zhang, Yuhao Wang, Sheng Lin, Peiyan Dong, Yen-Kuang Chen, Yuan Xie, Yanzhi Wang

As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.

Model Compression Network Pruning

Visual Tactile Fusion Object Clustering

no code implementations21 Nov 2019 Tao Zhang, Yang Cong, Gan Sun, Qianqian Wang, Zhenming Ding

To effectively benefit both visual and tactile modalities for object clustering, in this paper, we propose a deep Auto-Encoder-like Non-negative Matrix Factorization framework for visual-tactile fusion clustering.

Clustering Model Optimization +1

MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing

no code implementations COLING 2020 Tao Zhang, Congying Xia, Chun-Ta Lu, Philip Yu

Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types.

Entity Typing

Evolving Metric Learning for Incremental and Decremental Features

no code implementations27 Jun 2020 Jiahua Dong, Yang Cong, Gan Sun, Tao Zhang, Xu Tang, Xiaowei Xu

Online metric learning has been widely exploited for large-scale data classification due to the low computational cost.

Metric Learning

Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture

no code implementations2 Jul 2020 Jinhua Liang, Tao Zhang, Guoqing Feng

Aiming at channel compression, a novel convolutional construction named compact convolution is proposed to embrace the progress in spatial convolution, channel grouping and pooling operation.

Acoustic Scene Classification Event Detection +4

Re-weighting and 1-Point RANSAC-Based PnP Solution to Handle Outliers

no code implementations16 Jul 2020 Haoyin Zhou, Tao Zhang, Jagadeesan Jayender

We propose a fast PnP solution named R1PPnP to handle outliers by utilizing a soft re-weighting mechanism and the 1-point RANSAC scheme.

Fairness Constraints in Semi-supervised Learning

no code implementations14 Sep 2020 Tao Zhang, Tianqing Zhu, Mengde Han, Jing Li, Wanlei Zhou, Philip S. Yu

Extensive experiments show that our method is able to achieve fair semi-supervised learning, and reach a better trade-off between accuracy and fairness than fair supervised learning.

BIG-bench Machine Learning Fairness

Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination

no code implementations25 Sep 2020 Tao Zhang, Tianqing Zhu, Jing Li, Mengde Han, Wanlei Zhou, Philip S. Yu

A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.

BIG-bench Machine Learning Ensemble Learning +1

Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

no code implementations25 Sep 2020 Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen

Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.

Text Matching

Correlated Differential Privacy: Feature Selection in Machine Learning

no code implementations7 Oct 2020 Tao Zhang, Tianqing Zhu, Ping Xiong, Huan Huo, Zahir Tari, Wanlei Zhou

In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover, the privacy issue of data correlation in learning is guaranteed.

BIG-bench Machine Learning feature selection +1

Investigating Constraint Relationship in Evolutionary Many-Constraint Optimization

no code implementations9 Oct 2020 Mengjun Ming, Rui Wang, Tao Zhang

This paper contributes to the treatment of extensive constraints in evolutionary many-constraint optimization through consideration of the relationships between pair-wise constraints.

Limits on Axion Couplings from the first 80-day data of PandaX-II Experiment

no code implementations25 Jul 2017 Changbo Fu, Xiaopeng Zhou, Xun Chen, Yunhua Chen, Xiangyi Cui, Deqing Fang, Karl Giboni, Franco Giuliani, Ke Han, Xingtao Huang, Xiangdong Ji, Yonglin Ju, Siao Lei, Shaoli Li, Huaxuan Liu, Jianglai Liu, Yugang Ma, Yajun Mao, Xiangxiang Ren, Andi Tan, Hongwei Wang, Jimin Wang, Meng Wang, Qiuhong Wang, Siguang Wang, Xuming Wang, Zhou Wang, Shiyong Wu, Mengjiao Xiao, Pengwei Xie, Binbin Yan, Yong Yang, Jianfeng Yue, Hongguang Zhang, Tao Zhang, Li Zhao, Ning Zhou

We report new searches for the solar axions and galactic axion-like dark matter particles, using the first low-background data from PandaX-II experiment at China Jinping Underground Laboratory, corresponding to a total exposure of about $2. 7\times 10^4$ kg$\cdot$day.

High Energy Physics - Experiment Solar and Stellar Astrophysics High Energy Physics - Phenomenology

On Front-end Gain Invariant Modeling for Wake Word Spotting

no code implementations13 Oct 2020 Yixin Gao, Noah D. Stein, Chieh-Chi Kao, Yunliang Cai, Ming Sun, Tao Zhang, Shiv Vitaladevuni

Since the WW model is trained with the AFE-processed audio data, its performance is sensitive to AFE variations, such as gain changes.

Improving the Certified Robustness of Neural Networks via Consistency Regularization

no code implementations24 Dec 2020 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to be effective to train neural networks that are certifiably robust to the attacker.

Generative Partial Visual-Tactile Fused Object Clustering

no code implementations28 Dec 2020 Tao Zhang, Yang Cong, Gan Sun, Jiahua Dong, Yuyang Liu, Zhengming Ding

More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.

Clustering Generative Adversarial Network +2

Bootstrap inference for quantile-based modal regression

no code implementations1 Jun 2020 Tao Zhang, Kengo Kato, David Ruppert

Specifically, we propose to estimate the conditional mode by minimizing the derivative of the estimated conditional quantile function defined by smoothing the linear quantile regression estimator, and develop two bootstrap methods, a novel pivotal bootstrap and the nonparametric bootstrap, for our conditional mode estimator.

Statistics Theory Methodology Statistics Theory

On the Equilibrium Elicitation of Markov Games Through Information Design

no code implementations14 Feb 2021 Tao Zhang, Quanyan Zhu

An obedient principle is established which states that it is without loss of generality to focus on the direct information design when the information design incentivizes each agent to select the signal sent by the designer, such that the design process avoids the predictions of the agents' strategic selection behaviors.

Low Pass Filter for Anti-aliasing in Temporal Action Localization

no code implementations23 Apr 2021 Cece Jin, Yuanqi Chen, Ge Li, Tao Zhang, Thomas Li

This paper aims to verify the existence of aliasing in TAL methods and investigate utilizing low pass filters to solve this problem by inhibiting the high-frequency band.

Temporal Action Localization

Informational Design of Dynamic Multi-Agent System

no code implementations7 May 2021 Tao Zhang, Quanyan Zhu

We propose a direct information design approach that incentivizes each agent to select the signal sent by the principal, such that the design process avoids the predictions of the agents' strategic selection behaviors.

Pre-training Graph Neural Network for Cross Domain Recommendation

no code implementations16 Nov 2021 Chen Wang, Yueqing Liang, Zhiwei Liu, Tao Zhang, Philip S. Yu

Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain.

Graph Representation Learning Recommendation Systems

SEQUENCE MODELLING WITH AUTO-ADDRESSING AND RECURRENT MEMORY INTEGRATING NETWORKS

no code implementations27 Sep 2018 Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li

Processing sequential data with long term dependencies and learn complex transitions are two major challenges in many deep learning applications.

MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack

no code implementations29 Nov 2021 Mengting Xu, Tao Zhang, Daoqiang Zhang

However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks.

Adversarial Attack

End-to-end Alexa Device Arbitration

no code implementations8 Dec 2021 Jarred Barber, Yifeng Fan, Tao Zhang

We introduce a variant of the speaker localization problem, which we call device arbitration.

Bayesian Promised Persuasion: Dynamic Forward-Looking Multiagent Delegation with Informational Burning

no code implementations16 Jan 2022 Tao Zhang, Quanyan Zhu

A revelation-principle-like design regime is established to show that the persuasion with belief hierarchies can be fully characterized by correlating the randomization of the agents' local BPD mechanisms with the persuasion as a direct recommendation of the future promises.

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

no code implementations29 Jan 2022 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses.

Adversarial Attack Adversarial Defense

End-to-End Quality-of-Service Assurance with Autonomous Systems: 5G/6G Case Study

no code implementations31 Jan 2022 Van Sy Mai, Richard J. La, Tao Zhang, Abdella Battou

This paper presents a novel framework and a distributed algorithm that can enable ANs and CNs to autonomously "cooperate" with each other to dynamically negotiate their local QoS budgets and to collectively meet E2E QoS goals by sharing only their estimates of the global constraint functions, without disclosing their local decision variables.

Distributed Optimization

Federated Learning Challenges and Opportunities: An Outlook

no code implementations1 Feb 2022 Jie Ding, Eric Tramel, Anit Kumar Sahu, Shuang Wu, Salman Avestimehr, Tao Zhang

Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.

Federated Learning

RRL:Regional Rotation Layer in Convolutional Neural Networks

no code implementations25 Feb 2022 Zongbo Hao, Tao Zhang, Mingwang Chen, Kaixu Zhou

Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features.

Astronomy Image Classification +2

SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo

no code implementations27 Mar 2022 Tao Zhang

In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume.

Vocal Bursts Intensity Prediction

Leveraging Search History for Improving Person-Job Fit

no code implementations27 Mar 2022 Yupeng Hou, Xingyu Pan, Wayne Xin Zhao, Shuqing Bian, Yang song, Tao Zhang, Ji-Rong Wen

As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.

Text Matching

Self-Aware Personalized Federated Learning

no code implementations17 Apr 2022 Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang

In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.

Personalized Federated Learning Uncertainty Quantification

Deep Reinforcement Learning for Orienteering Problems Based on Decomposition

no code implementations25 Apr 2022 Wei Liu, Tao Zhang, Rui Wang, Kaiwen Li, Wenhua Li, Kang Yang

A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes.

reinforcement-learning Reinforcement Learning (RL) +1

ActPerFL: Active Personalized Federated Learning

no code implementations FL4NLP (ACL) 2022 Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, Tao Zhang

Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.

Personalized Federated Learning Uncertainty Quantification

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

no code implementations21 Jun 2022 Wei Liu, Rui Wang, Tao Zhang, Kaiwen Li, Wenhua Li, Hisao Ishibuchi

Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades.

Problem Decomposition reinforcement-learning +1

InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle

no code implementations23 Jun 2022 Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

Therefore, guaranteeing the robustness of hard examples is crucial for improving the final robustness of the model.

Challenges and Opportunities in Multi-device Speech Processing

no code implementations27 Jun 2022 Gregory Ciccarelli, Jarred Barber, Arun Nair, Israel Cohen, Tao Zhang

We review current solutions and technical challenges for automatic speech recognition, keyword spotting, device arbitration, speech enhancement, and source localization in multidevice home environments to provide context for the INTERSPEECH 2022 special session, "Challenges and opportunities for signal processing and machine learning for multiple smart devices".

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Large-scale matrix optimization based multi microgrid topology design with a constrained differential evolution algorithm

no code implementations18 Jul 2022 Wenhua Li, Shengjun Huang, Tao Zhang, Rui Wang, Ling Wang

Binary matrix optimization commonly arise in the real world, e. g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints.

Patient-Specific Game-Based Transfer Method for Parkinson's Disease Severity Prediction

no code implementations7 Aug 2022 Zaifa Xue, Huibin Lu, Tao Zhang, Max A. Little

Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction.

feature selection severity prediction

Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking

no code implementations24 Sep 2022 Shuiying Xiang, Tao Zhang, Shuqing Jiang, Yanan Han, YaHui Zhang, Chenyang Du, Xingxing Guo, Licun Yu, Yuechun Shi, Yue Hao

To our best knowledge, the performance of the Spiking SiamFC++ outperforms the existing state-of-the-art approaches in SNN-based object tracking, which provides a novel path for SNN application in the field of target tracking.

Object Object Tracking

Federated Learning with Server Learning: Enhancing Performance for Non-IID Data

no code implementations6 Oct 2022 Van Sy Mai, Richard J. La, Tao Zhang

Federated Learning (FL) has emerged as a means of distributed learning using local data stored at clients with a coordinating server.

Auxiliary Learning Federated Learning

BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction

no code implementations7 Nov 2022 Shiqing Wei, Tao Zhang, Shunping Ji, Muying Luo, Jianya Gong

Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images.

A Policy Optimization Method Towards Optimal-time Stability

no code implementations2 Jan 2023 Shengjie Wang, Fengbo Lan, Xiang Zheng, Yuxue Cao, Oluwatosin Oseni, Haotian Xu, Tao Zhang, Yang Gao

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization.

Reinforcement Learning (RL)

EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator

no code implementations3 Jan 2023 Mingzhe Li, Xiuying Chen, Weiheng Liao, Yang song, Tao Zhang, Dongyan Zhao, Rui Yan

The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.

Low-Rank Structured Clutter Covariance Matrix Estimation for Airborne STAP Radar

no code implementations27 Jan 2023 Tao Zhang, Haifang Zheng, Qijun Luo

In space-time adaptive processing (STAP) of the airborne radar system, it is very important to realize sparse restoration of the clutter covariance matrix with a small number of samples.

Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization

no code implementations28 Feb 2023 Haotian Xu, Shengjie Wang, Zhaolei Wang, Yunzhe Zhang, Qing Zhuo, Yang Gao, Tao Zhang

In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose.

Efficient Exploration Reinforcement Learning (RL)

Adversarial Attack with Raindrops

no code implementations28 Feb 2023 Jiyuan Liu, Bingyi Lu, Mingkang Xiong, Tao Zhang, Huilin Xiong

Extensive experiments are carried out to demonstrate that the images crafted by AdvRD are visually and statistically close to the natural raindrop images, can work as strong attackers to DNN models, and also help improve the robustness of DNNs to raindrop attacks.

Adversarial Attack Generative Adversarial Network

A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation

no code implementations27 Mar 2023 Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Tao Zhang

Symmetric bi-manual manipulation is essential for various on-orbit operations due to its potent load capacity.

Motion Planning

How human-derived brain organoids are built differently from brain organoids derived of genetically-close relatives: A multi-scale hypothesis

no code implementations17 Apr 2023 Tao Zhang, Sarthak Gupta, Madeline A. Lancaster, J. M. Schwarz

We postulate that the enhancement of ZEB2 expression driving this intermediate state is potentially due to chromatin reorganization.

Semi-Supervised Federated Learning for Keyword Spotting

no code implementations9 May 2023 Enmao Diao, Eric W. Tramel, Jie Ding, Tao Zhang

Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants.

Federated Learning Keyword Spotting

SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning

no code implementations30 May 2023 Tao Zhang, Wu Huang

Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples.

Classification Few-Shot Learning +1

Differences in boundary behavior in the 3D vertex and Voronoi models

no code implementations6 Jun 2023 Elizabeth Lawson-Keister, Tao Zhang, M. Lisa Manning

However, recent work in 2D has hinted that there may be differences between the two models in systems with heterotypic interfaces between two tissue types, and there is a burgeoning interest in 3D tissue models.

Open-Ended Question Answering

Learning to Branch in Combinatorial Optimization with Graph Pointer Networks

no code implementations4 Jul 2023 Rui Wang, Zhiming Zhou, Tao Zhang, Ling Wang, Xin Xu, Xiangke Liao, Kaiwen Li

The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions.

Combinatorial Optimization Variable Selection

Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning

no code implementations12 Jul 2023 Yunfei Guo, Tao Zhang, Wu Huang

Emotion recognition is an important research direction in artificial intelligence, helping machines understand and adapt to human emotional states.

Contrastive Learning EEG +1

Comprehensive Analysis of Network Robustness Evaluation Based on Convolutional Neural Networks with Spatial Pyramid Pooling

no code implementations10 Aug 2023 Wenjun Jiang, Tianlong Fan, Changhao Li, Chuanfu Zhang, Tao Zhang, Zong-fu Luo

However, the performance of the proposed CNN model varies: for evaluation tasks that are consistent with the trained network type, the proposed CNN model consistently achieves accurate evaluations of both attack curves and robustness values across all removal scenarios.

Flashlight Search Medial Axis: A Pixel-Free Pore-Network Extraction Algorithm

no code implementations5 Aug 2023 Jie Liu, Tao Zhang, Shuyu Sun

In this way, computational complexity of this method is greatly reduced compared to that of traditional pixel-based extraction methods, thus enabling large-scale pore-network extraction.

Dimensionality Reduction

DexCatch: Learning to Catch Arbitrary Objects with Dexterous Hands

no code implementations13 Oct 2023 Fengbo Lan, Shengjie Wang, Yunzhe Zhang, Haotian Xu, Oluwatosin Oseni, Yang Gao, Tao Zhang

Achieving human-like dexterous manipulation remains a crucial area of research in robotics.

Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling

no code implementations21 Dec 2023 Jie Han, Yixiong Zou, Haozhao Wang, Jun Wang, Wei Liu, Yao Wu, Tao Zhang, Ruixuan Li

Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available.

intent-classification Intent Classification +4

Training and Serving System of Foundation Models: A Comprehensive Survey

no code implementations5 Jan 2024 Jiahang Zhou, Yanyu Chen, Zicong Hong, Wuhui Chen, Yue Yu, Tao Zhang, Hui Wang, Chuanfu Zhang, Zibin Zheng

Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems.

Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation

no code implementations15 Jan 2024 Zhibo Xiao, Luwei Yang, Tao Zhang, Wen Jiang, Wei Ning, Yujiu Yang

Recently, a new recommendation scenario, called Trigger-Induced Recommendation (TIR), where users are able to explicitly express their instant interests via trigger items, is emerging as an essential role in many e-commerce platforms, e. g., Alibaba. com and Amazon.

Click-Through Rate Prediction

Episodic-free Task Selection for Few-shot Learning

no code implementations31 Jan 2024 Tao Zhang

In this framework, episodic tasks are not used directly for training, but for evaluating the effectiveness of some selected episodic-free tasks from a task set that are performed for training the meta-learners.

Contrastive Learning Few-Shot Learning

On Practical Diversified Recommendation with Controllable Category Diversity Framework

1 code implementation6 Feb 2024 Tao Zhang, Luwei Yang, Zhibo Xiao, Wen Jiang, Wei Ning

These neglected non-interaction preferences are especially important for broadening user's interests in alleviating echo chamber/filter bubble effects. Therefore, in this paper, we first define diversity as two distinct definitions, i. e., user-explicit diversity (U-diversity) and user-item non-interaction diversity (N-diversity) based on user historical behaviors.

Recommendation Systems

MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music

no code implementations15 Feb 2024 ZiHao Wang, Shuyu Li, Tao Zhang, Qi Wang, Pengfei Yu, Jinyang Luo, Yan Liu, Ming Xi, Kejun Zhang

To this end, we present MuChin, the first open-source music description benchmark in Chinese colloquial language, designed to evaluate the performance of multimodal LLMs in understanding and describing music.

Information Retrieval Music Information Retrieval

Search Intenion Network for Personalized Query Auto-Completion in E-Commerce

no code implementations5 Mar 2024 Wei Bao, Mi Zhang, Tao Zhang, Chengfu Huo

Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions. Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process, the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model. 2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer. However, the current intention extracted from prefix may be contrary to the historical preferences.

A Quick Framework for Evaluating Worst Robustness of Complex Networks

no code implementations28 Feb 2024 Wenjun Jiang, Peiyan Li, Tianlong Fan, Ting Li, Chuan-fu Zhang, Tao Zhang, Zong-fu Luo

Robustness is pivotal for comprehending, designing, optimizing, and rehabilitating networks, with simulation attacks being the prevailing evaluation method.

On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks

no code implementations7 Mar 2024 Bingkun Lai, Jiayi He, Jiawen Kang, Gaolei Li, Minrui Xu, Tao Zhang, Shengli Xie

Federated learning is a promising technique for effectively training GAI models in mobile edge networks due to its data distribution.

Federated Learning Quantization

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