Search Results for author: Zhi Chen

Found 66 papers, 17 papers with code

Deep Seam Prediction for Image Stitching Based on Selection Consistency Loss

no code implementations10 Feb 2023 Senmao Cheng, Fan Yang, Zhi Chen, Nanjun Yuan, Wenbin Tao

To our knowledge, the proposed DSeam is the first deep learning based seam prediction method for image stitching.

Image Stitching

On the Structural Generalization in Text-to-SQL

no code implementations12 Jan 2023 Jieyu Li, Lu Chen, Ruisheng Cao, Su Zhu, Hongshen Xu, Zhi Chen, Hanchong Zhang, Kai Yu

Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases.


Risk-Averse MDPs under Reward Ambiguity

no code implementations3 Jan 2023 Haolin Ruan, Zhi Chen, Chin Pang Ho

We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity.

Exploring the Whole Rashomon Set of Sparse Decision Trees

2 code implementations16 Sep 2022 Rui Xin, Chudi Zhong, Zhi Chen, Takuya Takagi, Margo Seltzer, Cynthia Rudin

We show three applications of the Rashomon set: 1) it can be used to study variable importance for the set of almost-optimal trees (as opposed to a single tree), 2) the Rashomon set for accuracy enables enumeration of the Rashomon sets for balanced accuracy and F1-score, and 3) the Rashomon set for a full dataset can be used to produce Rashomon sets constructed with only subsets of the data set.

THz ISAC: A Physical-Layer Perspective of Terahertz Integrated Sensing and Communication

no code implementations7 Sep 2022 Chong Han, Yongzhi Wu, Zhi Chen, Yi Chen, Guangjian Wang

In this article, challenges from THz channel and transceiver perspectives, as well as difficulties of ISAC are elaborated.


Profiling Television Watching Behaviour Using Bayesian Hierarchical Joint Models for Time-to-Event and Count Data

1 code implementation6 Sep 2022 Rafael A. Moral, Zhi Chen, Shuai Zhang, Sally McClean, Gabriel R. Palma, Brahim Allan, Ian Kegel

The model drastically reduces the dimensionality of the data from thousands of observations per customer to 11 customer-level parameter estimates and random effects.

Federated Zero-Shot Learning for Visual Recognition

no code implementations5 Sep 2022 Zhi Chen, Yadan Luo, Sen Wang, Jingjing Li, Zi Huang

We identify two key challenges in our FedZSL protocol: 1) the trained models are prone to be biased to the locally observed classes, thus failing to generalize to the unseen classes and/or seen classes appeared on other devices; 2) as each category in the training data comes from a single source, the central model is highly vulnerable to model replacement (backdoor) attacks.

Federated Learning Zero-Shot Learning

Improving Multi-Interest Network with Stable Learning

no code implementations14 Jul 2022 Zhaocheng Liu, Yingtao Luo, Di Zeng, Qiang Liu, Daqing Chang, Dongying Kong, Zhi Chen

Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems.

Recommendation Systems

GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning

no code implementations5 Jul 2022 Zhi Chen, Yadan Luo, Sen Wang, Jingjing Li, Zi Huang

To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.

Generalized Zero-Shot Learning

LPFS: Learnable Polarizing Feature Selection for Click-Through Rate Prediction

no code implementations1 Jun 2022 Yi Guo, Zhaocheng Liu, Jianchao Tan, Chao Liao, Sen yang, Lei Yuan, Dongying Kong, Zhi Chen, Ji Liu

When training is finished, some gates are exact zero, while others are around one, which is particularly favored by the practical hot-start training in the industry, due to no damage to the model performance before and after removing the features corresponding to exact-zero gates.

Click-Through Rate Prediction

SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation

no code implementations22 Apr 2022 Haiyang Huang, Zhi Chen, Cynthia Rudin

Experimental results provide evidence that our method can discover multiple concepts within a single image and outperforms state-of-the-art unsupervised methods on complex datasets such as Cityscapes and COCO-Stuff.

Unsupervised Semantic Segmentation

SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

1 code implementation28 Mar 2022 Zhi Chen, Kun Sun, Fan Yang, Wenbing Tao

In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.

Point Cloud Registration

Beam Training and Alignment for RIS-Assisted Millimeter Wave Systems:State of the Art and Beyond

no code implementations25 Mar 2022 Peilan Wang, Jun Fang, Weizheng Zhang, Zhi Chen, Hongbin Li, Wei zhang

The deployment of RIS, however, complicates the system architecture and poses a significant challenge for beam training (BT)/ beam alignment (BA), a process that is required to establish a reliable link between the transmitter and the receiver.

DFT-Spread Orthogonal Time Frequency Space System with Superimposed Pilots for Terahertz Integrated Sensing and Communication

no code implementations21 Feb 2022 Yongzhi Wu, Chong Han, Zhi Chen

Moreover, the effectiveness of the iterative method for data detection aided by superimposed pilots in DFT-s-OTFS systems is validated by the simulations and the bit error rate performance is not degraded by the Doppler effects.

Hyper-relationship Learning Network for Scene Graph Generation

no code implementations15 Feb 2022 Yibing Zhan, Zhi Chen, Jun Yu, Baosheng Yu, DaCheng Tao, Yong Luo

As a result, HLN significantly improves the performance of scene graph generation by integrating and reasoning from object interactions, relationship interactions, and transitive inference of hyper-relationships.

Graph Attention Graph Generation +1

Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers

no code implementations11 Feb 2022 Limin Yang, Zhi Chen, Jacopo Cortellazzi, Feargus Pendlebury, Kevin Tu, Fabio Pierazzi, Lorenzo Cavallaro, Gang Wang

Empirically, we show that existing backdoor attacks in malware classifiers are still detectable by recent defenses such as MNTD.

Backdoor Attack

SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration

no code implementations CVPR 2022 Zhi Chen, Kun Sun, Fan Yang, Wenbing Tao

In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.

Point Cloud Registration

Distinguishing Unseen From Seen for Generalized Zero-Shot Learning

no code implementations CVPR 2022 Hongzu Su, Jingjing Li, Zhi Chen, Lei Zhu, Ke Lu

In this paper, we present a novel method which leverages both visual and semantic modalities to distinguish seen and unseen categories.

Generalized Zero-Shot Learning

DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration

1 code implementation28 Dec 2021 Zhi Chen, Fan Yang, Wenbing Tao

In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration.

Point Cloud Registration Translation

Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF

no code implementations9 Dec 2021 Su Zhu, Lu Chen, Ruisheng Cao, Zhi Chen, Qingliang Miao, Kai Yu

In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU.

intent-classification Intent Classification +5

How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning

1 code implementation10 Nov 2021 Zhi Chen, Alexander Ogren, Chiara Daraio, L. Catherine Brinson, Cynthia Rudin

Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems.

Band Gap BIG-bench Machine Learning +1

Domain Adaptive Semantic Segmentation without Source Data

1 code implementation13 Oct 2021 Fuming You, Jingjing Li, Lei Zhu, Ke Lu, Zhi Chen, Zi Huang

To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore.

Semantic Segmentation

Adaptive Feedforward Reference Design for Active Vibration Rejection in Multi-Actuator Hard Disk Drives

no code implementations12 Oct 2021 Zhi Chen, Nikhil Potu Surya Prakash, Roberto Horowitz

In December 2017, Seagate unveiled the Multi Actuator Technology to double the data performance of the future generation hard disk drives (HDD).

Data-Driven Strictly Positive Real System Identification with prior System Knowledge

no code implementations12 Oct 2021 Nikhil Potu Surya Prakash, Zhi Chen, Roberto Horowitz

Strictly Positive Real (SPR) transfer functions arise in many areas of engineering like passivity theory in circuit analysis and adaptive control to name a few.

Sensing Integrated DFT-Spread OFDM Waveform and Deep Learning-powered Receiver Design for Terahertz Integrated Sensing and Communication Systems

no code implementations30 Sep 2021 Yongzhi Wu, Filip Lemic, Chong Han, Zhi Chen

One step forward, THz integrated sensing and communication (ISAC) system can realize both unprecedented data rates and millimeter-level accurate sensing.

System Identification in Multi-Actuator Hard Disk Drives with Colored Noises using Observer/Kalman Filter Identification (OKID) Framework

no code implementations25 Sep 2021 Nikhil Potu Surya Prakash, Zhi Chen, Roberto Horowitz

Multi Actuator Technology in Hard Disk drives (HDDs) equips drives with two dual stage actuators (DSA) each comprising of a voice coil motor (VCM) actuator and a piezoelectric micro actuator (MA) operating on the same pivot point.

Time Series Analysis

A Sparsity Algorithm with Applications to Corporate Credit Rating

no code implementations21 Jul 2021 Dan Wang, Zhi Chen, Ionut Florescu

We apply the sparsity algorithm to provide a simple suggestion to publicly traded companies in order to improve their credit ratings.

Counterfactual Explanation

Mitigating Generation Shifts for Generalized Zero-Shot Learning

1 code implementation7 Jul 2021 Zhi Chen, Yadan Luo, Sen Wang, Ruihong Qiu, Jingjing Li, Zi Huang

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e. g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training.

Generalized Zero-Shot Learning

CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation

1 code implementation6 Jul 2021 Ruihong Qiu, Sen Wang, Zhi Chen, Hongzhi Yin, Zi Huang

Existing visually-aware models make use of the visual features as a separate collaborative signal similarly to other features to directly predict the user's preference without considering a potential bias, which gives rise to a visually biased recommendation.

Counterfactual Inference Recommendation Systems

Bring Your Own Codegen to Deep Learning Compiler

no code implementations3 May 2021 Zhi Chen, Cody Hao Yu, Trevor Morris, Jorn Tuyls, Yi-Hsiang Lai, Jared Roesch, Elliott Delaye, Vin Sharma, Yida Wang

Deep neural networks (DNNs) have been ubiquitously applied in many applications, and accelerators are emerged as an enabler to support the fast and efficient inference tasks of these applications.

Code Generation

Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning

1 code implementation24 Apr 2021 Zhi Chen, Jiang Duan, Li Kang, Guoping Qiu

In addition to using the conditional GAN to generate class balanced supplementary training data, an innovative ensemble learning loss function ensuring each discriminator makes up for the deficiencies of the others is designed to overcome the class imbalanced problem, and an active learning algorithm is introduced to significantly reduce the cost of labeling real-world data.

Active Learning Ensemble Learning +1

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

no code implementations NAACL 2021 Zhi Chen, Lu Chen, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu, Kai Yu

Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query.

Semantic Parsing Text-To-SQL

Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences

1 code implementation31 Jan 2021 Zhi Chen, Fan Yang, Wenbing Tao

We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA).

Semantics Disentangling for Generalized Zero-Shot Learning

1 code implementation ICCV 2021 Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, Zheng Zhang

Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.

Generalized Zero-Shot Learning

Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning

no code implementations9 Jan 2021 Zhi Chen, Zi Huang, Jingjing Li, Zheng Zhang

To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes.

Generalized Zero-Shot Learning

Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation

no code implementations ICCV 2021 Zhi Chen, Xiaoqing Ye, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang

Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.

Monocular Depth Estimation Stereo Matching

Frequency Separation based Adaptive Feedforward Control for Rejecting Wideband Vibration with Application to Hard Disk Drives

no code implementations9 Dec 2020 Jinwen Pan, Zhi Chen, Yong Wang, Roberto Horowitz

Starting from the first region, the feedforward control parameters are learned simultaneously with the low order plant model in the same region and then moves to the next region until all the regions are performed.

Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management

no code implementations22 Sep 2020 Zhi Chen, Lu Chen, Xiaoyuan Liu, Kai Yu

The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e. g., hotel booking).

Decision Making Dialogue Management +3

Structured Hierarchical Dialogue Policy with Graph Neural Networks

no code implementations22 Sep 2020 Zhi Chen, Xiaoyuan Liu, Lu Chen, Kai Yu

A novel ComNet is proposed to model the structure of a hierarchical agent.

CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

no code implementations22 Sep 2020 Zhi Chen, Lu Chen, Zihan Xu, Yanbin Zhao, Su Zhu, Kai Yu

In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history.

Dialogue State Tracking

Dual Learning for Dialogue State Tracking

no code implementations22 Sep 2020 Zhi Chen, Lu Chen, Yanbin Zhao, Su Zhu, Kai Yu

In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history.

Dialogue State Tracking

Deep Reinforcement Learning for On-line Dialogue State Tracking

no code implementations22 Sep 2020 Zhi Chen, Lu Chen, Xiang Zhou, Kai Yu

To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems.

Dialogue Management Dialogue State Tracking +4

Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches

no code implementations27 Jul 2020 Zhi Chen, Sen Wang, Jingjing Li, Zi Huang

A voting strategy averages the probability distributions output from the classifiers and, given that some patches are more discriminative than others, a discrimination-based attention mechanism helps to weight each patch accordingly.

Ensemble Learning Fine-Grained Image Classification +1

Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry

no code implementations11 Jul 2020 Zhi Chen, Fan Yang, Wenbing Tao

We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA).

Fully Automated 3D Segmentation of MR-Imaged Calf Muscle Compartments: Neighborhood Relationship Enhanced Fully Convolutional Network

no code implementations21 Jun 2020 Zhihui Guo, Honghai Zhang, Zhi Chen, Ellen van der Plas, Laurie Gutmann, Daniel Thedens, Peggy Nopoulos, Milan Sonka

Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction.

Edge Detection Image Segmentation +1

Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference

no code implementations4 Jun 2020 Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, Yida Wang

Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.

Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders

no code implementations30 Apr 2020 Yanbin Zhao, Lu Chen, Zhi Chen, Kai Yu

When modeling simple and complex sentences with autoencoders, we introduce different types of noise into the training process.

Denoising Language Modelling +4

Concept Whitening for Interpretable Image Recognition

1 code implementation5 Feb 2020 Zhi Chen, Yijie Bei, Cynthia Rudin

What does a neural network encode about a concept as we traverse through the layers?

Time-aware Gradient Attack on Dynamic Network Link Prediction

no code implementations24 Nov 2019 Jinyin Chen, Jian Zhang, Zhi Chen, Min Du, Qi Xuan

In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP).

Adversarial Attack Link Prediction +1

GLA-Net: An Attention Network with Guided Loss for Mismatch Removal

no code implementations28 Sep 2019 Zhi Chen, Fan Yang, Wenbing Tao

To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly.

CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language

no code implementations21 Sep 2019 Zhi Chen, Jingjing Li, Yadan Luo, Zi Huang, Yang Yang

Thus, a multi-modal cycle-consistency loss between the synthesized semantic representations and the ground truth can be learned and leveraged to enforce the generated semantic features to approximate to the real distribution in semantic space.

Zero-Shot Learning

Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Joint Active and Passive Precoding Design

no code implementations28 Aug 2019 Peilan Wang, Jun Fang, Xiaojun Yuan, Zhi Chen, Huiping Duan, Hongbin Li

In this framework, we study joint active and passive precoding design for IRS-assisted mmWave systems, where multiple IRSs are deployed to assist the data transmission from a base station (BS) to a single-antenna receiver.

AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning

no code implementations27 May 2019 Lu Chen, Zhi Chen, Bowen Tan, Sishan Long, Milica Gasic, Kai Yu

Experiments show that AgentGraph models significantly outperform traditional reinforcement learning approaches on most of the 18 tasks of the PyDial benchmark.

Dialogue Management Management +4

Supervised and Semi-Supervised Deep Neural Networks for CSI-Based Authentication

no code implementations25 Jul 2018 Qian Wang, Hang Li, Zhi Chen, Dou Zhao, Shuang Ye, Jiansheng Cai

In addition, we propose to use the convolutional recurrent neural network (CRNN)---a combination of the CNN and the RNN---to learn local and contextual information in CSI for user authentication.

Low-Rank Tensor Decomposition-Aided Channel Estimation for Millimeter Wave MIMO-OFDM Systems

1 code implementation12 Sep 2016 Zhou Zhou, Jun Fang, Linxiao Yang, Hongbin Li, Zhi Chen, Rick S. Blum

Different from most existing studies that are concerned with narrowband channels, we consider estimation of wideband mmWave channels with frequency selectivity, which is more appropriate for mmWave MIMO-OFDM systems.

Information Theory Information Theory

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