Search Results for author: Zhiwei Wang

Found 49 papers, 13 papers with code

Improving Paratope and Epitope Prediction by Multi-Modal Contrastive Learning and Interaction Informativeness Estimation

1 code implementation31 May 2024 Zhiwei Wang, Yongkang Wang, Wen Zhang

Additionally, the ablation studies and visualizations demonstrate the superiority of MIPE owing to the better representations acquired through multi-modal contrastive learning and the interaction patterns comprehended by the interaction informativeness estimation.

Contrastive Learning Informativeness

Exploring Graph-based Knowledge: Multi-Level Feature Distillation via Channels Relational Graph

no code implementations14 May 2024 Zhiwei Wang, Jun Huang, Longhua Ma, Chengyu Wu, Hongyu Ma

In visual tasks, large teacher models capture essential features and deep information, enhancing performance.

Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing

no code implementations8 May 2024 Zhongwang Zhang, Pengxiao Lin, Zhiwei Wang, Yaoyu Zhang, Zhi-Qin John Xu

Transformers have shown impressive capabilities across various tasks, but their performance on compositional problems remains a topic of debate.

Loss Jump During Loss Switch in Solving PDEs with Neural Networks

no code implementations6 May 2024 Zhiwei Wang, Lulu Zhang, Zhongwang Zhang, Zhi-Qin John Xu

Further experiments reveal that this phenomenon arises from the different frequency preferences of neural networks under different loss functions.

StyleSeg V2: Towards Robust One-shot Segmentation of Brain Tissue via Optimization-free Registration Error Perception

no code implementations6 May 2024 Zhiwei Wang, Xiaoyu Zeng, Chongwei Wu, Jinxin Lv, Xu Zhang, Wei Fang, Qiang Li

One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images for seg-model by warping a carefully-labeled atlas.

One-Shot Segmentation

MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint

no code implementations1 Apr 2024 Qiang Hu, Zhenyu Yi, Ying Zhou, Ting Li, Fan Huang, Mei Liu, Qiang Li, Zhiwei Wang

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption.

Multiple Instance Learning Segmentation

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

no code implementations21 Feb 2024 Zhiwei Wang, Huazheng Wang, Hongning Wang

Our analysis shows that against two popularly employed MAB algorithms, UCB1 and $\epsilon$-greedy, the success of a stealthy attack depends on the environmental conditions and the realized reward of the arm pulled in the first round.

Multi-Armed Bandits

Anchor function: a type of benchmark functions for studying language models

no code implementations16 Jan 2024 Zhongwang Zhang, Zhiwei Wang, Junjie Yao, Zhangchen Zhou, Xiaolong Li, Weinan E, Zhi-Qin John Xu

However, language model research faces significant challenges, especially for academic research groups with constrained resources.

Language Modelling

IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors

no code implementations11 Oct 2023 Zhiwei Wang, Qiang Hu, Hongkuan Shi, Li He, Man He, Wenxuan Dai, Ting Li, Yitong Zhang, Dun Li, Mei Liu, Qiang Li

In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA.


Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks

no code implementations27 Aug 2023 Xin Yang, Yi Lin, Zhiwei Wang, Xin Li, Kwang-Ting Cheng

A method for measuring the synthesis complexity is proposed to automatically determine the synthesis order in our sequential GAN.

Generative Adversarial Network Image Generation

Dual-view Correlation Hybrid Attention Network for Robust Holistic Mammogram Classification

1 code implementation19 Jun 2023 Zhiwei Wang, Junlin Xian, Kangyi Liu, Xin Li, Qiang Li, Xin Yang

Mammogram image is important for breast cancer screening, and typically obtained in a dual-view form, i. e., cranio-caudal (CC) and mediolateral oblique (MLO), to provide complementary information.

Clinical Knowledge

MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Information

1 code implementation5 Mar 2023 Zhiwei Wang, Fa Zhang, Cong Zheng, Xianghong Hu, Mingxuan Cai, Can Yang

Here, we consider a matrix factorization problem by utilizing auxiliary information, which is massively available in real-world applications, to overcome the challenges caused by poor data quality.

Variational Inference

Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation

1 code implementation26 Nov 2022 Jinxin Lv, Xiaoyu Zeng, Sheng Wang, Ran Duan, Zhiwei Wang, Qiang Li

In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues.

One-Shot Segmentation Segmentation

Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions

1 code implementation15 Oct 2022 Hongkuan Shi, Zhiwei Wang, Ying Zhou, Dun Li, Xin Yang, Qiang Li

The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS).

3D Reconstruction Disparity Estimation

Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs

no code implementations5 Jun 2022 Zhiwei Wang, Jinxin Lv, Yunqiao Yang, Yuanhuai Liang, Yi Lin, Qiang Li, Xin Li, Xin Yang

Vertebral landmark localization is a crucial step for variant spine-related clinical applications, which requires detecting the corner points of 17 vertebrae.

A deep learning-based model reduction (DeePMR) method for simplifying chemical kinetics

no code implementations6 Jan 2022 Zhiwei Wang, Yaoyu Zhang, Enhan Zhao, Yiguang Ju, Weinan E, Zhi-Qin John Xu, Tianhan Zhang

The mechanism reduction is modeled as an optimization problem on Boolean space, where a Boolean vector, each entry corresponding to a species, represents a reduced mechanism.

Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion

1 code implementation25 Sep 2021 Jinxin Lv, Zhiwei Wang, Hongkuan Shi, Haobo Zhang, Sheng Wang, Yilang Wang, Qiang Li

Registration of brain MRI images requires to solve a deformation field, which is extremely difficult in aligning intricate brain tissues, e. g., subcortical nuclei, etc.

Deep Natural Language Processing for LinkedIn Search

no code implementations16 Aug 2021 Weiwei Guo, Xiaowei Liu, Sida Wang, Michaeel Kazi, Zhiwei Wang, Zhoutong Fu, Jun Jia, Liang Zhang, Huiji Gao, Bo Long

Building a successful search system requires a thorough understanding of textual data semantics, where deep learning based natural language processing techniques (deep NLP) can be of great help.

Document Ranking Language Modelling

ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline

no code implementations SEMEVAL 2021 Jiaju Lin, Jing Ling, Zhiwei Wang, Jiawei Liu, Qin Chen, Liang He

The purpose of the task was to extract triples from a paper in the Nature Language Processing field for constructing an Open Research Knowledge Graph.

Open Information Extraction

Power System Transient Modeling and Simulation using Integrated Circuit

no code implementations6 Jun 2021 Xiang Zhang, Renchang Dai, Peng Wei, Yijing Liu, Guangyi Liu, Zhiwei Wang

Transient stability analysis (TSA) plays an important role in power system analysis to investigate the stability of power system.

Numerical Integration

Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning

no code implementations6 Dec 2020 Tao Luo, Zheng Ma, Zhiwei Wang, Zhi-Qin John Xu, Yaoyu Zhang

A supervised learning problem is to find a function in a hypothesis function space given values on isolated data points.

Defocus Blur Detection via Salient Region Detection Prior

no code implementations19 Nov 2020 Ming Qian, Min Xia, Chunyi Sun, Zhiwei Wang, Liguo Weng

Defocus blur Detection aims to separate the out-of-focus and depth-of-field areas in photos, which is an important work in computer vision.

Defocus Blur Detection

Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection

1 code implementation31 Aug 2020 Zhiwei Wang, Zhengzhang Chen, Jingchao Ni, Hui Liu, Haifeng Chen, Jiliang Tang

To address these challenges, in this paper, we propose OC4Seq, a multi-scale one-class recurrent neural network for detecting anomalies in discrete event sequences.

Anomaly Detection

Evaluating Load Models and Their Impacts on Power Transfer Limits

no code implementations7 Aug 2020 Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Siqi Wang, Ruisheng Diao, Zhiwei Wang

Since the load dynamics have substantial impacts on power system transient stability, load models are one critical factor that affects the power transfer limits.


Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models

no code implementations27 May 2020 Haochen Liu, Zhiwei Wang, Tyler Derr, Jiliang Tang

Recently, neural network based dialogue systems have become ubiquitous in our increasingly digitalized society.

Siamese Neural Networks for Class Activity Detection

no code implementations15 May 2020 Hang Li, Zhiwei Wang, Jiliang Tang, Wenbiao Ding, Zitao Liu

Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms.

Action Detection Activity Detection

2D-Dirac surface states and bulk gap probed via quantum capacitance in a 3D topological insulator

no code implementations5 Dec 2019 Jimin Wang, Cosimo Gorini, Klaus Richter, Zhiwei Wang, Yoichi Ando, Dieter Weiss

BiSbTeSe$_2$ is a 3D topological insulator (3D-TI) with Dirac type surface states and low bulk carrier density, as donors and acceptors compensate each other.

Mesoscale and Nanoscale Physics

Learning Multi-level Dependencies for Robust Word Recognition

2 code implementations22 Nov 2019 Zhiwei Wang, Hui Liu, Jiliang Tang, Songfan Yang, Gale Yan Huang, Zitao Liu

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises.

Two-stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach

no code implementations8 Nov 2019 Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Zhiwei Wang

However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters.


Automatic Short Answer Grading via Multiway Attention Networks

no code implementations23 Sep 2019 Tiaoqiao Liu, Wenbiao Ding, Zhiwei Wang, Jiliang Tang, Gale Yan Huang, Zitao Liu

Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads.

Deep Knowledge Tracing with Side Information

no code implementations1 Sep 2019 Zhiwei Wang, Xiaoqin Feng, Jiliang Tang, Gale Yan Huang, Zitao Liu

Monitoring student knowledge states or skill acquisition levels known as knowledge tracing, is a fundamental part of intelligent tutoring systems.

Knowledge Tracing

Recommender Systems with Heterogeneous Side Information

1 code implementation18 Jul 2019 Tianqiao Liu, Zhiwei Wang, Jiliang Tang, Songfan Yang, Gale Yan Huang, Zitao Liu

In modern recommender systems, both users and items are associated with rich side information, which can help understand users and items.

Recommendation Systems

Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning

no code implementations24 Apr 2019 Ruisheng Diao, Zhiwei Wang, Di Shi, Qianyun Chang, Jiajun Duan, Xiaohu Zhang

Modern power grids are experiencing grand challenges caused by the stochastic and dynamic nature of growing renewable energy and demand response.

AI Agent reinforcement-learning +1

Probabilistic Load Forecasting via Point Forecast Feature Integration

no code implementations26 Mar 2019 Qicheng Chang, Yishen Wang, Xiao Lu, Di Shi, Haifeng Li, Jiajun Duan, Zhiwei Wang

In the first stage, all related features are utilized to train a point forecast model and also obtain the feature importance.

energy management Feature Importance +3

Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

no code implementations26 Mar 2019 Yayu Peng, Yishen Wang, Xiao Lu, Haifeng Li, Di Shi, Zhiwei Wang, Jie Li

Short-term load forecasting (STLF) is essential for the reliable and economic operation of power systems.

Load Forecasting

Submodular Load Clustering with Robust Principal Component Analysis

no code implementations20 Feb 2019 Yishen Wang, Xiao Lu, Yiran Xu, Di Shi, Zhehan Yi, Jiajun Duan, Zhiwei Wang

Traditional load analysis is facing challenges with the new electricity usage patterns due to demand response as well as increasing deployment of distributed generations, including photovoltaics (PV), electric vehicles (EV), and energy storage systems (ESS).

Clustering Load Forecasting

Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization

no code implementations17 Dec 2018 Zhiwei Wang, Yi Lin, Kwang-Ting Cheng, Xin Yang

Experimental results show that our method can effectively synthesize a large variety of mpMRI images which contain meaningful CS PCa lesions, display a good visual quality and have the correct paired relationship.

Synthesizing Multi-Parameter Magnetic Resonance Imaging (Mp-Mri) Data

A Neural-Network-Based Optimal Control of Ultra-Capacitors with System Uncertainties

no code implementations29 Nov 2018 Jiajun Duan, Zhehan Yi, Di Shi, Hao Xu, Zhiwei Wang

Conventional control strategies usually produce large disturbances to buses during charging and discharging (C&D) processes of UCs, which significantly degrades the power quality and system performance, especially under fast C&D modes.

Point Tracking

A Rprop-Neural-Network-Based PV Maximum Power Point Tracking Algorithm with Short-Circuit Current Limitation

no code implementations29 Nov 2018 Yao Cui, Zhehan Yi, Jiajun Duan, Di Shi, Zhiwei Wang

This paper proposes a resilient-backpropagation-neural-network-(Rprop-NN) based algorithm for Photovoltaic (PV) maximum power point tracking (MPPT).

Point Tracking

Power Market Price Forecasting via Deep Learning

no code implementations18 Sep 2018 Yongli Zhu, Songtao Lu, Renchang Dai, Guangyi Liu, Zhiwei Wang

Then the raw input and output data are preprocessed by unit scaling, and the trained network is tested on the real price data under different input lengths, forecasting horizons and data sizes.

Linked Recurrent Neural Networks

no code implementations19 Aug 2018 Zhiwei Wang, Yao Ma, Dawei Yin, Jiliang Tang

Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation.

Document Classification Machine Translation +3

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI

1 code implementation Elsevier 2017 Xin Yang, Chaoyue Liu, Zhiwei Wang, Jun Yang, Hung Le Min, Liang Wang, Kwang-Ting (Tim) Cheng

Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions’ locations.

General Classification

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