Search Results for author: Liang Chen

Found 75 papers, 28 papers with code

Enhanced Sparse Model for Blind Deblurring

no code implementations ECCV 2020 Liang Chen, Faming Fang, Shen Lei, Fang Li, Guixu Zhang

Specifically, we use a weighted combination of a dense function (i. e. l2) and a newly designed enhanced sparse model termed as le, which is developed from two sparse models (i. e. l1 and l0), to fulfill the task.


OID: Outlier Identifying and Discarding in Blind Image Deblurring

no code implementations ECCV 2020 Liang Chen, Faming Fang, Jiawei Zhang, Jun Liu, Guixu Zhang

Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.

Blind Image Deblurring Image Deblurring

Spiking Graph Convolutional Networks

1 code implementation5 May 2022 Zulun Zhu, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu, Siqiang Luo

Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information.

Graph Classification Recommendation Systems

A Survey of Deep Learning Models for Structural Code Understanding

1 code implementation3 May 2022 Ruoting Wu, Yuxin Zhang, Qibiao Peng, Liang Chen, Zibin Zheng

In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights.

FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation

no code implementations2 May 2022 Yuansheng Wang, Wangbin Sun, Kun Xu, Zulun Zhu, Liang Chen, Zibin Zheng

Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect.

Classification Contrastive Learning +4

GUARD: Graph Universal Adversarial Defense

1 code implementation20 Apr 2022 Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Jiawang Dan, Changhua Meng, Zibin Zheng, Weiqiang Wang

Graph convolutional networks (GCNs) have shown to be vulnerable to small adversarial perturbations, which becomes a severe threat and largely limits their applications in security-critical scenarios.

Adversarial Defense

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs

2 code implementations19 Apr 2022 Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing.

Ranked #6 on AMR Parsing on LDC2017T10 (using extra training data)

AMR Parsing Dependency Parsing +1

Self-Calibrated Efficient Transformer for Lightweight Super-Resolution

1 code implementation19 Apr 2022 Wenbin Zou, Tian Ye, Weixin Zheng, Yunchen Zhang, Liang Chen, Yi Wu

Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance.

Image Super-Resolution

Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

1 code implementation23 Mar 2022 Liang Chen, Yong Zhang, Yibing Song, Lingqiao Liu, Jue Wang

Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations.

DeepFake Detection Face Swapping +1

Exact mean-field models for spiking neural networks with adaptation

no code implementations16 Mar 2022 Liang Chen, Sue Ann Campbell

Networks of spiking neurons with adaption have been shown to be able to reproduce a wide range of neural activities, including the emergent population bursting and spike synchrony that underpin brain disorders and normal function.

CAR: Class-aware Regularizations for Semantic Segmentation

1 code implementation arXiv:2203.07160 2022 Ye Huang, Di Kang, Liang Chen, Xuefei Zhe, Wenjing Jia, Xiangjian He, Linchao Bao

Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules.

Representation Learning Semantic Segmentation

Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation

2 code implementations6 Mar 2022 Liang Chen, Runxin Xu, Baobao Chang

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.

Machine Translation Translation

Faithful learning with sure data for lung nodule diagnosis

no code implementations25 Feb 2022 Hanxiao Zhang, Liang Chen, Xiao Gu, Minghui Zhang, Yulei Qin, Feng Yao, Zhexin Wang, Yun Gu, Guang-Zhong Yang

In this study, we construct a sure dataset with pathologically-confirmed labels and propose a collaborative learning framework to facilitate sure nodule classification by integrating unsure data knowledge through nodule segmentation and malignancy score regression.

Lung Nodule Classification

Enhanced DeepONet for Modeling Partial Differential Operators Considering Multiple Input Functions

no code implementations17 Feb 2022 Lesley Tan, Liang Chen

We propose new Enhanced DeepONet or EDeepONet high-level neural network structure, in which two input functions are represented by two branch DNN sub-networks, which are then connected with output truck network via inner product to generate the output of the whole neural network.

Recent Advances in Reliable Deep Graph Learning: Adversarial Attack, Inherent Noise, and Distribution Shift

no code implementations15 Feb 2022 Bingzhe Wu, Jintang Li, Chengbin Hou, Guoji Fu, Yatao Bian, Liang Chen, Junzhou Huang

Despite the progress, applying DGL to real-world applications faces a series of reliability threats including adversarial attacks, inherent noise, and distribution shift.

Adversarial Attack Graph Learning

Robust Dynamic State Estimator of Integrated Energy Systems based on Natural Gas Partial Differential Equations

no code implementations4 Feb 2022 Liang Chen, Yang Li, Manyun Huang, Xinxin Hui, Songlin Gu

A novel robust dynamic state estimation methodology for integrated natural gas and electric power systems is proposed based on Kalman filter.

Neighboring Backdoor Attacks on Graph Convolutional Network

no code implementations17 Jan 2022 Liang Chen, Qibiao Peng, Jintang Li, Yang Liu, Jiawei Chen, Yong Li, Zibin Zheng

To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node.

Backdoor Attack

Carrier Phase Ranging for Indoor Positioning with 5G NR Signals

no code implementations22 Dec 2021 Liang Chen, Xin Zhou, Feifei Chen, Lie-Liang Yang, Ruizhi Chen

Indoor positioning is one of the core technologies of Internet of Things (IoT) and artificial intelligence (AI), and is expected to play a significant role in the upcoming era of AI.

Perceiving and Modeling Density is All You Need for Image Dehazing

no code implementations18 Nov 2021 Tian Ye, Mingchao Jiang, Yunchen Zhang, Liang Chen, ErKang Chen, Pen Chen, Zhiyong Lu

However, due to the paradox caused by the variation of real captured haze and the fixed degradation parameters of the current networks, the generalization ability of recent dehazing methods on real-world hazy images is not ideal. To address the problem of modeling real-world haze degradation, we propose to solve this problem by perceiving and modeling density for uneven haze distribution.

Image Dehazing Single Image Dehazing

Hierarchical Curriculum Learning for AMR Parsing

1 code implementation ACL 2022 Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.

AMR Parsing Representation Learning

SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring

1 code implementation12 Oct 2021 Wenbin Zou, Mingchao Jiang, Yunchen Zhang, Liang Chen, Zhiyong Lu, Yi Wu

On this basis, we reduce the number of up-sampling and down-sampling and design a simple network structure.

Deblurring Image Deblurring

Surprisingly Popular Algorithm-based Adaptive Euclidean Distance Topology Learning PSO

no code implementations25 Aug 2021 Xuan Wu, Jizong Han, Quanlong Cui, Liang Chen, Yanchun Liang, Han Huang, Heow Pueh Lee, You Zhou, Chunguo Wu

And then we propose the Surprisingly Popular Algorithm-based Adaptive Euclidean Distance Topology Learning Particle Swarm Optimization (SpadePSO), which uses SPA to guide the search direction of the exploitation sub-population, and analyze the influence of different topologies on SPA.

DGCN: Diversified Recommendation with Graph Convolutional Networks

1 code implementation16 Aug 2021 Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li

These years much effort has been devoted to improving the accuracy or relevance of the recommendation system.

Collaborative Filtering

Understanding Structural Vulnerability in Graph Convolutional Networks

1 code implementation13 Aug 2021 Liang Chen, Jintang Li, Qibiao Peng, Yang Liu, Zibin Zheng, Carl Yang

In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i. e., the weighted mean) of GCNs.

Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation

no code implementations7 Aug 2021 Shengsen Wu, Liang Chen, Yihang Lou, Yan Bai, Tao Bai, Minghua Deng, Lingyu Duan

Therefore, backward-compatible representation is proposed to enable "new" features to be compared with "old" features directly, which means that the database is active when there are both "new" and "old" features in it.

Contrastive Learning

Physics-Enforced Modeling for Insertion Loss of Transmission Lines by Deep Neural Networks

no code implementations27 Jul 2021 Liang Chen, Lesley Tan

In the second method, a third-order polynomial expression is defined first, which ensures positiveness, to approximate the insertion loss, then DeepONet neural network structure, which was proposed recently for function and system modeling, was employed to model the coefficients of polynomials.

Dynamic State Estimation for Integrated Natural Gas and Electric Power Systems

no code implementations13 Jul 2021 Liang Chen, Xinxin Hui, Songlin Gu, Manyun Huang, Yang Li

Boundary conditions of pipeline networks are used as supplementary constraints in the system model.

Blind Deblurring for Saturated Images

no code implementations CVPR 2021 Liang Chen, Jiawei Zhang, Songnan Lin, Faming Fang, Jimmy S. Ren

To address this problem, we introduce a new blur model to fit both saturated and unsaturated pixels, and all informative pixels can be considered during deblurring process.


Learning a Non-Blind Deblurring Network for Night Blurry Images

no code implementations CVPR 2021 Liang Chen, Jiawei Zhang, Jinshan Pan, Songnan Lin, Faming Fang, Jimmy S. Ren

Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels.

Deblurring Image Restoration

DNA-GCN: Graph convolutional networks for predicting DNA-protein binding

1 code implementation2 Jun 2021 Yuhang Guo, Xiao Luo, Liang Chen, Minghua Deng

Predicting DNA-protein binding is an important and classic problem in bioinformatics.

Signal Acquisition of Luojia-1A Low Earth Orbit Navigation Augmentation System with Software Defined Receiver

no code implementations31 May 2021 Liang Chen, Xiangchen Lu, Nan Shen, Lei Wang, Yuan Zhuang, Ye Su, Deren Li, Ruizhi Chen

The performance of those integration algorithms on expanding the successful acquisition time range is verified by the real data collected from the Luojia-1A satellite.

AutoDebias: Learning to Debias for Recommendation

1 code implementation10 May 2021 Jiawei Chen, Hande Dong, Yang Qiu, Xiangnan He, Xin Xin, Liang Chen, Guli Lin, Keping Yang

This provides a valuable opportunity to develop a universal solution for debiasing, e. g., by learning the debiasing parameters from data.

Imputation Meta-Learning +1

Personalized Bundle Recommendation in Online Games

no code implementations12 Apr 2021 Qilin Deng, Kai Wang, Minghao Zhao, Zhene Zou, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.

Link Prediction Recommendation Systems

Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation

no code implementations7 Apr 2021 Kai Wang, Zhene Zou, Qilin Deng, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen, Peng Cui

As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.

Model-based Reinforcement Learning Recommendation Systems +1

Neural Architecture Search based on Cartesian Genetic Programming Coding Method

no code implementations12 Mar 2021 Xuan Wu, Linhan Jia, Xiuyi Zhang, Liang Chen, Yanchun Liang, You Zhou, Chunguo Wu

To evolve the architectures under the framework of CGP, the operations such as convolution are identified as the types of function nodes of CGP, and the evolutionary operations are designed based on Evolutionary Strategy.

Neural Architecture Search Sentence Classification

Robust Kalman filter-based dynamic state estimation of natural gas pipeline networks

no code implementations26 Feb 2021 Liang Chen, Peng Jin, Jing Yang, Yang Li, Yi Song

To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.

A High-dimensional Sparse Fourier Transform in the Continuous Setting

no code implementations22 Feb 2021 Liang Chen

In this paper, we theoretically propose a new hashing scheme to establish the sparse Fourier transform in high-dimensional space.

Data Structures and Algorithms Information Theory Numerical Analysis Information Theory Numerical Analysis 41A63 G.1.2; F.2.1

GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software

1 code implementation16 Feb 2021 Jintang Li, Kun Xu, Liang Chen, Zibin Zheng, Xiao Liu

Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.

Material absorption-based carrier generation model for modeling optoelectronic devices

no code implementations12 Feb 2021 Liang Chen, Hakan Bagci

The generation rate of photocarriers in optoelectronic materials is commonly calculated using the Poynting vector in the frequency domain.

Optics Computational Engineering, Finance, and Science Computational Physics

A possible blazar spectral irregularity case caused by photon--axionlike-particle oscillations

no code implementations11 Feb 2021 Jianeng Zhou, Zhongxiang Wang, Feng Huang, Liang Chen

We investigate this possibility by fitting the spectrum with the photon-ALP oscillation model, and find that the parameter space of ALP mass $m_a\leq 10^{-8}$\, eV and the coupling constant (between photons and ALPs) $g_{a\gamma}$=1. 16--1. 48$\times 10^{-10}$\, GeV$^{-1}$ can provide a fit to the line-like feature, while the magnetic field at the emission site of $\gamma$-rays is fixed at 0. 7\, G.

High Energy Astrophysical Phenomena

Lower Bound on the Optimal Access Bandwidth of ($K+2,K,2$)-MDS Array Code with Degraded Read Friendly

no code implementations4 Feb 2021 Ting-Yi Wu, Yunghsiang S. Han, Zhengrui Li, Bo Bai, Gong Zhang, Liang Chen, Xiang Wu

Accessing the data in the failed disk (degraded read) with low latency is crucial for an erasure-coded storage system.

Information Theory Information Theory

Matching Function Equilibria with Partial Assignment: Existence, Uniqueness and Estimation

no code implementations3 Feb 2021 Liang Chen, Eugene Choo, Alfred Galichon, Simon Weber

In this paper, we argue that models coming from a variety of fields share a common structure that we call matching function equilibria with partial assignment.

Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control

no code implementations21 Jan 2021 Qiong Wu, Xu Chen, Zhi Zhou, Liang Chen, Junshan Zhang

To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity.


Decoding PPP Corrections from BDS B2b Signals Using a Software-defined Receiver: an Initial Performance Evaluation

no code implementations27 Nov 2020 Xiangchen Lu, Liang Chen, Nan Shen, Lei Wang, Zhenhang Jiao, Ruizhi Chen

With the rapid development of China's BeiDou Navigation Satellite System(BDS), the application of real-time precise point positioning (RTPPP) based on BDS has become an active research area in the field of Global Navigation Satellite System (GNSS).

Learning to Sample the Most Useful Training Patches from Images

no code implementations24 Nov 2020 Shuyang Sun, Liang Chen, Gregory Slabaugh, Philip Torr

Some image restoration tasks like demosaicing require difficult training samples to learn effective models.


Ensembled CTR Prediction via Knowledge Distillation

no code implementations8 Nov 2020 Jieming Zhu, Jinyang Liu, Weiqi Li, Jincai Lai, Xiuqiang He, Liang Chen, Zibin Zheng

Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications.

Click-Through Rate Prediction Knowledge Distillation

GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs

no code implementations3 Nov 2020 Yunpeng Weng, Xu Chen, Liang Chen, Wei Liu

Most existing GNN models exploit a single type of aggregator (e. g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node.

Graph Attention Link Prediction +1

Self-supervised Graph Learning for Recommendation

1 code implementation21 Oct 2020 Jiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He, Liang Chen, Jianxun Lian, Xing Xie

In this work, we explore self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation.

Graph Learning Representation Learning +1

Stochastic Time-Periodic Tonelli Lagrangian on Compact Manifold

no code implementations21 Sep 2020 Liang Chen

In this paper, we study a class of time-periodic stochastic Tonelli Lagrangians on compact manifolds.

Dynamical Systems

Adversarial Attack on Large Scale Graph

1 code implementation8 Sep 2020 Jintang Li, Tao Xie, Liang Chen, Fenfang Xie, Xiangnan He, Zibin Zheng

Currently, most works on attacking GNNs are mainly using gradient information to guide the attack and achieve outstanding performance.

Adversarial Attack

Variance-reduced Language Pretraining via a Mask Proposal Network

no code implementations12 Aug 2020 Liang Chen

In particular, we first propose a principled gradient variance decomposition theorem, which shows that the variance of the stochastic gradient of the language pretraining can be naturally decomposed into two terms: the variance that arises from the sample of data in a batch, and the variance that arises from the sampling of the mask.

Self-Supervised Learning

Interactive Path Reasoning on Graph for Conversational Recommendation

no code implementations1 Jul 2020 Wenqiang Lei, Gangyi Zhang, Xiangnan He, Yisong Miao, Xiang Wang, Liang Chen, Tat-Seng Chua

Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user preference.

Recommendation Systems

Crossed-Time Delay Neural Network for Speaker Recognition

2 code implementations31 May 2020 Liang Chen, Yanchun Liang, Xiaohu Shi, You Zhou, Chunguo Wu

Time Delay Neural Network (TDNN) is a well-performing structure for DNN-based speaker recognition systems.

Speaker Recognition Speaker Verification

Secure Deep Graph Generation with Link Differential Privacy

1 code implementation1 May 2020 Carl Yang, Haonan Wang, Ke Zhang, Liang Chen, Lichao Sun

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).

Graph Generation Link Prediction

Modelling High-Order Social Relations for Item Recommendation

no code implementations23 Mar 2020 Yang Liu, Liang Chen, Xiangnan He, Jiaying Peng, Zibin Zheng, Jie Tang

The prevalence of online social network makes it compulsory to study how social relations affect user choice.

A Survey of Adversarial Learning on Graphs

2 code implementations10 Mar 2020 Liang Chen, Jintang Li, Jiaying Peng, Tao Xie, Zengxu Cao, Kun Xu, Xiangnan He, Zibin Zheng, Bingzhe Wu

To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically.

Graph Clustering Link Prediction +1

DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network

no code implementations9 Mar 2020 Qiong Wu, Muhong Wu, Xu Chen, Zhi Zhou, Kaiwen He, Liang Chen

Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users' QoE.

Decision Making

Data Poisoning Attacks on Neighborhood-based Recommender Systems

no code implementations1 Dec 2019 Liang Chen, Yangjun Xu, Fenfang Xie, Min Huang, Zibin Zheng

2) the fake users can be transferred to attack the state-of-the-art collaborative filtering recommender systems such as Neural Collaborative Filtering and Bayesian Personalized Ranking Matrix Factorization.

Collaborative Filtering Data Poisoning +1

The Intrinsic Properties of Brain Based on the Network Structure

no code implementations2 Nov 2019 Xiang Zou, Lie Yao, Donghua Zhao, Liang Chen, Ying Mao

The dynamic of the equation set can be described by some basic equations, which is based on the mathematical derivation.

Decision Making

Selecting Reliable Blockchain Peers via Hybrid Blockchain Reliability Prediction

1 code implementation31 Oct 2019 PeiLin Zheng, Zibin Zheng, Liang Chen

Blockchain and blockchain-based decentralized applications are attracting increasing attentions recently.

Software Engineering Distributed, Parallel, and Cluster Computing

Intelligent image synthesis to attack a segmentation CNN using adversarial learning

no code implementations24 Sep 2019 Liang Chen, Paul Bentley, Kensaku MORI, Kazunari Misawa, Michitaka Fujiwara, Daniel Rueckert

Our approach has three key features: 1) The generated adversarial examples exhibit anatomical variations (in form of deformations) as well as appearance perturbations; 2) The adversarial examples attack segmentation models so that the Dice scores decrease by a pre-specified amount; 3) The attack is not required to be specified beforehand.

Image Generation Semantic Segmentation

A New CGAN Technique for Constrained Topology Design Optimization

no code implementations22 Jan 2019 M. -H. Herman Shen, Liang Chen

This paper presents a new conditional GAN (named convex relaxing CGAN or crCGAN) to replicate the conventional constrained topology optimization algorithms in an extremely effective and efficient process.

Learning Semantic Representations for Unsupervised Domain Adaptation

1 code implementation ICML 2018 Shaoan Xie, Zibin Zheng, Liang Chen, Chuan Chen

Prior domain adaptation methods address this problem through aligning the global distribution statistics between source domain and target domain, but a drawback of prior methods is that they ignore the semantic information contained in samples, e. g., features of backpacks in target domain might be mapped near features of cars in source domain.

Learning Semantic Representations Unsupervised Domain Adaptation

Attention-Gated Networks for Improving Ultrasound Scan Plane Detection

6 code implementations15 Apr 2018 Jo Schlemper, Ozan Oktay, Liang Chen, Jacqueline Matthew, Caroline Knight, Bernhard Kainz, Ben Glocker, Daniel Rueckert

We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance.

Object Recognition Based on Amounts of Unlabeled Data

no code implementations25 Mar 2016 Fuqiang Liu, Fukun Bi, Liang Chen

Using 2% labeled data and 98% unlabeled data, the accuracies of the proposed method on the two data sets are 78. 39% and 50. 77% respectively.

Object Recognition

Boost Picking: A Universal Method on Converting Supervised Classification to Semi-supervised Classification

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Yiding Yang, Liang Chen

It is theoretically proved that Boost Picking could train a supervised model mainly by un-labeled data as effectively as the same model trained by 100% labeled data, only if recalls of the two weak classifiers are all greater than zero and the sum of precisions is greater than one.

Classification General Classification

Feature-Area Optimization: A Novel SAR Image Registration Method

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Liang Chen, Hao Shi, Wei Liu

This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO).

Image Registration

Dual Linear Regression Based Classification for Face Cluster Recognition

no code implementations CVPR 2014 Liang Chen

Considering that the image vectors of each subject, either in gallery or in probe, span a subspace; an algorithm, Dual Linear Regression Classification (DLRC), for the face cluster recognition problem is developed where the distance between two subspaces is defined as the similarity value between a gallery subject and a probe subject.

Classification General Classification

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