7 code implementations • 7 May 2019 • Yu Wang, Quan Zhou, Jia Liu, Jian Xiong, Guangwei Gao, Xiaofu Wu, Longin Jan Latecki
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #29 on Real-Time Semantic Segmentation on Cityscapes test
2 code implementations • 24 Jun 2019 • Yu Wang, Quan Zhou, Xiaofu Wu
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
Ranked #28 on Real-Time Semantic Segmentation on Cityscapes test
1 code implementation • 22 Aug 2021 • Kai-Hsun Chen, Huan-Ping Su, Wei-Chiu Chuang, Hung-Chang Hsiao, Wangda Tan, Zhankun Tang, Xun Liu, Yanbo Liang, Wen-Chih Lo, Wanqiang Ji, Byron Hsu, Keqiu Hu, HuiYang Jian, Quan Zhou, Chien-Min Wang
As machine learning is applied more widely, it is necessary to have a machine learning platform for both infrastructure administrators and users including expert data scientists and citizen data scientists to improve their productivity.
3 code implementations • 28 May 2018 • Suofei Zhang, Wei Zhao, Xiaofu Wu, Quan Zhou
Capsules as well as dynamic routing between them are most recently proposed structures for deep neural networks.
Ranked #5 on Image Classification on smallNORB
2 code implementations • 15 May 2021 • Hanfeng Zhai, Quan Zhou, Guohui Hu
We apply the traditional DNN and our BubbleNet to train the coarsened simulation data and predict the physics fields of both the two bubbly flow cases.
1 code implementation • 2 Nov 2019 • Jia Liu, Quan Zhou, Yong Qiang, Bin Kang, Xiaofu Wu, Baoyu Zheng
The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.
1 code implementation • 4 Aug 2021 • Suofei Zhang, Zirui Yin, Xiofu Wu, Kun Wang, Quan Zhou, Bin Kang
In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure.
Ranked #6 on Person Re-Identification on CUHK03 labeled
1 code implementation • 1 Sep 2022 • ZiCheng Zhang, Wei Sun, Xiongkuo Min, Quan Zhou, Jun He, Qiyuan Wang, Guangtao Zhai
In specific, we split the point clouds into sub-models to represent local geometry distortions such as point shift and down-sampling.
Ranked #1 on Point Cloud Quality Assessment on SJTU-PCQA
1 code implementation • 5 Feb 2020 • Xiaofu Wu, Suofei hang, Quan Zhou, Zhen Yang, Chunming Zhao, Longin Jan Latecki
Entropy minimization has been widely used in unsupervised domain adaptation (UDA).
Ranked #7 on Domain Adaptation on ImageCLEF-DA
2 code implementations • 28 Sep 2022 • Quan Zhou, Huimin Shi, Weikang Xiang, Bin Kang, Xiaofu Wu, Longin Jan Latecki
The recent advances of compressing high-accuracy convolution neural networks (CNNs) have witnessed remarkable progress for real-time object detection.
Ranked #13 on Object Detection on PASCAL VOC 2007
1 code implementation • 17 Jun 2022 • Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Hu
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity.
1 code implementation • 5 Mar 2023 • Yu-Neng Chuang, Guanchu Wang, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Hu
In this work, we propose a COntrastive Real-Time eXplanation (CoRTX) framework to learn the explanation-oriented representation and relieve the intensive dependence of explainer training on explanation labels.
1 code implementation • 21 Mar 2020 • Quan Zhou, Dechun Cong, Bin Kang, Xiaofu Wu, Baoyu Zheng, Huimin Lu, Longin Jan Latecki
Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation.
1 code implementation • 4 Feb 2020 • Quan Zhou, Jakub Marecek
There has been much recent progress in forecasting the next observation of a linear dynamical system (LDS), which is known as the improper learning, as well as in the estimation of its system matrices, which is known as the proper learning of LDS.
1 code implementation • 12 Sep 2022 • Quan Zhou, Jakub Marecek, Robert N. Shorten
We also show that by exploiting sparsity in the convexifications, we can reduce the run time of our methods considerably.
no code implementations • 25 Sep 2017 • Xin Jin, Shuyun Zhu, Le Wu, Geng Zhao, Xiao-Dong Li, Quan Zhou, Huimin Lu
In this work, a multi-level chaotic maps models for 3D textured encryption was presented by observing the different contributions for recognizing cipher 3D models between vertices (point cloud), polygons and textures.
no code implementations • 6 Sep 2014 • Quan Zhou, Wenlin Chen, Shiji Song, Jacob R. Gardner, Kilian Q. Weinberger, Yixin Chen
Our second contribution is to derive a practical algorithm based on this reduction.
no code implementations • 12 Jun 2017 • Peizhe Tang, Quan Zhou, Shou-Cheng Zhang
Exotic massless fermionic excitations with non-zero Berry flux, other than Dirac and Weyl fermions, could exist in condensed matter systems under the protection of crystalline symmetries, such as spin-1 excitations with 3-fold degeneracy and spin-3/2 Rarita-Schwinger-Weyl fermions.
Materials Science Mesoscale and Nanoscale Physics Applied Physics
no code implementations • 31 Jan 2019 • Mingming Zhang, Quan Zhou, Yanlang Hu
In this paper, we propose a lossless data hiding scheme in JPEG images.
no code implementations • 6 Mar 2020 • Kaichen Zhou, Shiji Song, Gao Huang, Wu Cheng, Quan Zhou
Specifically, the proposed algorithm can be used to estimate the upper and lower bounds of the updated classifier's coefficient matrix with a low computational complexity related to the size of the updated dataset.
no code implementations • 23 Mar 2020 • Lie Ju, Xin Wang, Quan Zhou, Hu Zhu, Mehrtash Harandi, Paul Bonnington, Tom Drummond, ZongYuan Ge
We design a regularisation technique to regulate the domain adaptation.
no code implementations • 12 Jun 2020 • Quan Zhou, Jakub Marecek, Robert N. Shorten
In machine learning, training data often capture the behaviour of multiple subgroups of some underlying human population.
no code implementations • 11 Jan 2021 • Quan Zhou, Hyunwoong Chang
A series of high-dimensional consistency results is obtained, including the strong selection consistency of an empirical Bayes model for structure learning.
Statistics Theory Computation Statistics Theory 62F15, 62J05
no code implementations • 23 Feb 2021 • Jeremiah Duncan, Fabian Fallas, Chris Gropp, Emily Herron, Maria Mahbub, Paula Olaya, Eduardo Ponce, Tabitha K. Samuel, Daniel Schultz, Sudarshan Srinivasan, Maofeng Tang, Viktor Zenkov, Quan Zhou, Edmon Begoli
To this end, and using those established techniques, we first developed an experimental frame-work for author detection and input perturbations.
no code implementations • 22 Oct 2014 • Philip A. Ernst, Michael B. Imerman, Larry Shepp, Quan Zhou
During the Great Recession, Democrats in the United States argued that government spending could be utilized to "grease the wheels" of the economy in order to create wealth and to increase employment; Republicans, on the other hand, contended that government spending is wasteful and discouraged investment, thereby increasing unemployment.
1 code implementation • 4 Jun 2021 • Quan Zhou, Jakub Marecek, Robert N. Shorten
In the process, we introduce a novel notion of subgroup fairness (which we call Inter-fairness), which can be combined with other notions of fairness within each subgroup (called Intra-fairness), and the utility for the customers (Customer-Care) in the objective of the market-clearing problem.
no code implementations • 31 Oct 2021 • Linjie Wang, Quan Zhou, Chenfeng Jiang, Xiaofu Wu, Longin Jan Latecki
Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years.
no code implementations • 31 Oct 2021 • Huimin Shi, Quan Zhou, Yinghao Ni, Xiaofu Wu, Longin Jan Latecki
Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices.
no code implementations • 9 Jun 2022 • Wei Lu, Wei Sun, Xiongkuo Min, Wenhan Zhu, Quan Zhou, Jun He, Qiyuan Wang, ZiCheng Zhang, Tao Wang, Guangtao Zhai
In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality.
no code implementations • 3 Sep 2022 • Quan Zhou, Ramen Ghosh, Robert Shorten, Jakub Marecek
In a closed-loop view of the AI system and its users, the equal treatment concerns one pass through the loop.
no code implementations • 6 Sep 2022 • Min Hua, Zhi Li, Quan Zhou
The study suggested that the MADRL with an independence ratio of 0. 2 is the best, and more than 2. 4% of energy can be saved over the conventional DRL framework.
no code implementations • 18 Dec 2022 • Jincheng Hu, Yang Lin, Jihao Li, Zhuoran Hou, Dezong Zhao, Quan Zhou, Jingjing Jiang, Yuanjian Zhang
The empirical analysis is developed in four aspects: algorithm, perception and decision granularity, hyperparameters, and reward function.
no code implementations • 25 Jan 2023 • Chengqian Ma, Zhiqiang Wu, Chunlei Cai, Pengwei Zhang, Yi Wang, Long Zheng, Chao Chen, Quan Zhou
In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec.
no code implementations • 16 Mar 2023 • Min Hua, Cetengfei Zhang, Fanggang Zhang, Zhi Li, Xiaoli Yu, Hongming Xu, Quan Zhou
The recently emerging multi-mode plug-in hybrid electric vehicle (PHEV) technology is one of the pathways making contributions to decarbonization, and its energy management requires multiple-input and multipleoutput (MIMO) control.
no code implementations • CAAI 2023 • Mingwei Wen, Quan Zhou, Bo Tao, Pavel Shcherbakov, Yang Xu, Xuming Zhang
Tumour segmentation in medical images (especially 3D tumour segmentation) is highly challenging due to the possible similarity between tumours and adjacent tissues, occurrence of multiple tumours and variable tumour shapes and sizes.
no code implementations • 13 Apr 2023 • Guanxun Li, Aaron Smith, Quan Zhou
Informed importance tempering (IIT) is an easy-to-implement MCMC algorithm that can be seen as an extension of the familiar Metropolis-Hastings algorithm with the special feature that informed proposals are always accepted, and which was shown in Zhou and Smith (2022) to converge much more quickly in some common circumstances.
no code implementations • 28 Aug 2023 • Min Hua, Bin Shuai, Quan Zhou, Jinhai Wang, Yinglong He, Hongming Xu
The evolution of EMS from HEVs to connected hybrid electric vehicles (CHEVs) represent a pivotal shift.
no code implementations • 14 Sep 2023 • Babak Naderi, Ross Cutler, Nabakumar Singh Khongbantabam, Yasaman Hosseinkashi, Henrik Turbell, Albert Sadovnikov, Quan Zhou
We present the Video Conferencing Dataset (VCD) for evaluating video codecs for real-time communication, the first such dataset focused on video conferencing.
1 code implementation • 17 Oct 2023 • Quan Zhou, Jakub Marecek
Fairness holds a pivotal role in the realm of machine learning, particularly when it comes to addressing groups categorised by sensitive attributes, e. g., gender, race.
no code implementations • 3 Nov 2023 • Mengjia Niu, Xiaoyu He, Petr Ryšavý, Quan Zhou, Jakub Marecek
Clustering of time series is a well-studied problem, with applications ranging from quantitative, personalized models of metabolism obtained from metabolite concentrations to state discrimination in quantum information theory.
no code implementations • 4 Mar 2024 • Jhanvi Garg, Xianyang Zhang, Quan Zhou
Schr\"{o}dinger bridge can be viewed as a continuous-time stochastic control problem where the goal is to find an optimally controlled diffusion process whose terminal distribution coincides with a pre-specified target distribution.
no code implementations • 1 Apr 2024 • Haitao Li, You Chen, Zhekai Ge, Qingyao Ai, Yiqun Liu, Quan Zhou, Shuai Huo
Legal retrieval techniques play an important role in preserving the fairness and equality of the judicial system.
no code implementations • 5 Apr 2024 • Hyunwoong Chang, Quan Zhou
Convergence analysis of Markov chain Monte Carlo methods in high-dimensional statistical applications is increasingly recognized.