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.
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.
1 code implementation • ACL 2022 • Liang Chen, Runxin Xu, Baobao Chang
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
1 code implementation • 5 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.
1 code implementation • 3 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.
no code implementations • 2 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.
1 code implementation • 20 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.
2 code implementations • 19 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)
1 code implementation • 19 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.
1 code implementation • 23 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.
no code implementations • 16 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.
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.
Ranked #3 on
Semantic Segmentation
on PASCAL Context
2 code implementations • 6 Mar 2022 • Liang Chen, Runxin Xu, Baobao Chang
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
no code implementations • 25 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.
no code implementations • 17 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.
no code implementations • 15 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.
no code implementations • 4 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.
no code implementations • 17 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.
no code implementations • 22 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.
no code implementations • 18 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.
Ranked #1 on
Image Dehazing
on Haze4k
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.
1 code implementation • 12 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.
no code implementations • 25 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.
1 code implementation • 16 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.
1 code implementation • 13 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.
1 code implementation • 7 Aug 2021 • Chen Chen, Chen Qin, Cheng Ouyang, Zeju Li, Shuo Wang, Huaqi Qiu, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert
The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training.
no code implementations • 7 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.
no code implementations • 27 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.
no code implementations • 13 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.
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.
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.
1 code implementation • 2 Jun 2021 • Yuhang Guo, Xiao Luo, Liang Chen, Minghua Deng
Predicting DNA-protein binding is an important and classic problem in bioinformatics.
no code implementations • 31 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.
1 code implementation • Findings (ACL) 2021 • Yulong Chen, Yang Liu, Liang Chen, Yue Zhang
Proposal of large-scale datasets has facilitated research on deep neural models for news summarization.
1 code implementation • 10 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.
no code implementations • 12 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.
no code implementations • 7 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
no code implementations • 12 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.
no code implementations • 26 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.
no code implementations • 22 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
1 code implementation • 16 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.
no code implementations • 12 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
no code implementations • 11 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
no code implementations • 4 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
no code implementations • 3 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.
no code implementations • 21 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.
no code implementations • 27 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).
no code implementations • 24 Nov 2020 • Shuyang Sun, Liang Chen, Gregory Slabaugh, Philip Torr
Some image restoration tasks like demosaicing require difficult training samples to learn effective models.
no code implementations • 8 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.
no code implementations • 3 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.
1 code implementation • 21 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.
no code implementations • 21 Sep 2020 • Liang Chen
In this paper, we study a class of time-periodic stochastic Tonelli Lagrangians on compact manifolds.
Dynamical Systems
3 code implementations • 15 Sep 2020 • Kai Zhang, Martin Danelljan, Yawei Li, Radu Timofte, Jie Liu, Jie Tang, Gangshan Wu, Yu Zhu, Xiangyu He, Wenjie Xu, Chenghua Li, Cong Leng, Jian Cheng, Guangyang Wu, Wenyi Wang, Xiaohong Liu, Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong, Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan, Xiaochuan Li, Zhiqiang Lang, Jiangtao Nie, Wei Wei, Lei Zhang, Abdul Muqeet, Jiwon Hwang, Subin Yang, JungHeum Kang, Sung-Ho Bae, Yongwoo Kim, Geun-Woo Jeon, Jun-Ho Choi, Jun-Hyuk Kim, Jong-Seok Lee, Steven Marty, Eric Marty, Dongliang Xiong, Siang Chen, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Haicheng Wang, Vineeth Bhaskara, Alex Levinshtein, Stavros Tsogkas, Allan Jepson, Xiangzhen Kong, Tongtong Zhao, Shanshan Zhao, Hrishikesh P. S, Densen Puthussery, Jiji C. V, Nan Nan, Shuai Liu, Jie Cai, Zibo Meng, Jiaming Ding, Chiu Man Ho, Xuehui Wang, Qiong Yan, Yuzhi Zhao, Long Chen, Jiangtao Zhang, Xiaotong Luo, Liang Chen, Yanyun Qu, Long Sun, Wenhao Wang, Zhenbing Liu, Rushi Lan, Rao Muhammad Umer, Christian Micheloni
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
1 code implementation • 8 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.
no code implementations • 12 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.
no code implementations • 1 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.
1 code implementation • 23 Jun 2020 • Chen Chen, Chen Qin, Huaqi Qiu, Cheng Ouyang, Shuo Wang, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert
In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation.
2 code implementations • 31 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.
1 code implementation • 1 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).
no code implementations • 23 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.
2 code implementations • 10 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.
no code implementations • 9 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.
no code implementations • 1 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.
no code implementations • 2 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.
1 code implementation • 31 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
no code implementations • 24 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.
no code implementations • CVPR 2019 • Liang Chen, Faming Fang, Tingting Wang, Guixu Zhang
Blind image deblurring aims to recover sharp image from a blurred one while the blur kernel is unknown.
no code implementations • 22 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.
no code implementations • 25 Oct 2018 • Christopher Bowles, Liang Chen, Ricardo Guerrero, Paul Bentley, Roger Gunn, Alexander Hammers, David Alexander Dickie, Maria Valdés Hernández, Joanna Wardlaw, Daniel Rueckert
One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets.
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.
Ranked #7 on
Domain Adaptation
on SVHN-to-MNIST
Learning Semantic Representations
Unsupervised Domain Adaptation
6 code implementations • 15 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.
no code implementations • 25 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.
no code implementations • 18 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.
no code implementations • 18 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).
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.