检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Hu, Hao Han, Song Yang, Yihao Liu, Dongjue Xue, Haoran Liu, Gui-Geng Cheng, Zheyu Wang, Qi Jie Zhang, Shuang Zhang, Baile Luo, Yu School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China ZJU-Hangzhou Global Science and Technology Innovation Center Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang Zhejiang University Hangzhou310027 China International Joint Innovation Center ZJU-UIUC Institute Zhejiang University Haining314400 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 21 Nanyang Link Singapore637371 Singapore Department of Physics University of Hong Kong Hong Kong Department of Electrical & Electronic Engineering University of Hong Kong China Centre for Disruptive Photonic Technologies Nanyang Technological University Singapore637371 Singapore

The topological band theory predicts that bulk materials with nontrivial topological phases support topological edge states. This phenomenon is universal for various wave systems and has been widely observed for electromagnetic and acoustic waves. Here, we extend the notion of band topology from wave to diffusion dynamics. Unlike the wave systems that are usually Hermitian, the diffusion systems are anti-Hermitian with purely imaginary eigenvalues corresponding to decay rates. Via direct probe of the temperature diffusion, we experimentally retrieve the Hamiltonian of a thermal lattice, and observe the emergence of topological edge decays within the gap of bulk decays. Our results show that such edge states exhibit robust decay rates, which are topologically protected against disorders. This work constitutes a thermal analogue of topological insulators and paves the way to exploring defect-immune heat dissipation. Copyright © 2021, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Constraints on Ultra Heavy Dark Matter Properties from Dwarf Spheroidal Galaxies with LHAASO Observations

arXiv

引用

arXiv 2024年

作者： Cao, Zhen Aharonian, F. An, Q. Axikegu Bai, Y.X. Bao, Y.W. Bastieri, D. Bi, X.J. Bi, Y.J. Cai, J.T. Cao, Q. Cao, W.Y. Cao, Zhe Chang, J. Chang, J.F. Chen, A.M. Chen, E.S. Chen, Liang Chen, Lin Chen, Long Chen, M.J. Chen, M.L. Chen, Q.H. Chen, S.H. Chen, S.Z. Chen, T.L. Chen, Y. Cheng, N. Cheng, Y.D. Cui, M.Y. Cui, S.W. Cui, X.H. Cui, Y.D. Dai, B.Z. Dai, H.L. Dai, Z.G. Danzengluobu della Volpe, D. Dong, X.Q. Duan, K.K. Fan, J.H. Fan, Y.Z. Fang, J. Fang, K. Feng, C.F. Feng, L. Feng, S.H. Feng, X.T. Feng, Y.L. Gabici, S. Gao, B. Gao, C.D. Gao, L.Q. Gao, Q. Gao, W. Gao, W.K. Ge, M.M. Geng, L.S. Giacinti, G. Gong, G.H. Gou, Q.B. Gu, M.H. Guo, F.L. Guo, X.L. Guo, Y.Q. Guo, Y.Y. Han, Y.A. He, H.H. He, H.N. He, J.Y. He, X.B. He, Y. Heller, M. Hor, Y.K. Hou, B.W. Hou, C. Hou, X. Hu, H.B. Hu, Q. Hu, S.C. Huang, D.H. Huang, T.Q. Huang, W.J. Huang, X.T. Huang, X.Y. Huang, Y. Huang, Z.C. Ji, X.L. Jia, H.Y. Jia, K. Jiang, K. Jiang, X.W. Jiang, Z.J. Jin, M. Kang, M.M. Ke, T. Kuleshov, D. Kurinov, K. Li, B.B. Li, Cheng Li, Cong Li, D. Li, F. Li, H.B. Li, H.C. Li, H.Y. Li, J. Li, Jian Li, Jie Li, K. Li, W.L. Li, W.L. Li, X.R. Li, Xin Li, Y.Z. Li, Zhe Li, Zhuo Liang, E.W. Liang, Y.F. Lin, S.J. Liu, B. Liu, C. Liu, D. Liu, H. Liu, H.D. Liu, J. Liu, J.L. Liu, J.Y. Liu, M.Y. Liu, R.Y. Liu, S.M. Liu, W. Liu, Y. Liu, Y.N. Lu, R. Luo, Q. Lv, H.K. Ma, B.Q. Ma, L.L. Ma, X.H. Mao, J.R. Min, Z. Mitthumsiri, W. Mu, H.J. Nan, Y.C. Neronov, A. Ou, Z.W. Pang, B.Y. Pattarakijwanich, P. Pei, Z.Y. Qi, M.Y. Qi, Y.Q. Qiao, B.Q. Qin, J.J. Ruffolo, D. Sáiz, A. Semikoz, D. Shao, C.Y. Shao, L. Shchegolev, O. Sheng, X.D. Shu, F.W. Song, H.C. Stenkin, Yu.V. Stepanov, V. Su, Y. Sun, Q.N. Sun, X.N. Sun, Z.B. Key Laboratory of Particle Astrophysics Experimental Physics Division Computing Center Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China Tianfu Cosmic Ray Research Center Sichuan Chengdu610000 China Dublin Institute for Advanced Studies 31 Fitzwilliam Place 2 Dublin Ireland Max-Planck-Institut for Nuclear Physics P.O. Box 103980 Heidelberg69029 Germany State Key Laboratory of Particle Detection and Electronics China University of Science and Technology of China Anhui Hefei230026 China School of Physical Science and Technology School of Information Science and Technology Southwest Jiaotong University Sichuan Chengdu610031 China School of Astronomy and Space Science Nanjing University Jiangsu Nanjing210023 China Center for Astrophysics Guangzhou University Guangdong Guangzhou510006 China Hebei Normal University Hebei Shijiazhuang050024 China Key Laboratory of Dark Matter and Space Astronomy Key Laboratory of Radio Astronomy Purple Mountain Observatory Chinese Academy of Sciences Jiangsu Nanjing210023 China Tsung-Dao Lee Institute School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai200030 China Key Laboratory of Cosmic Rays Tibet University Ministry of Education Tibet Lhasa850000 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Sun Yat-sen University Guangdong Zhuhai519000 China Guangdong Guangzhou510275 China Sun Yat-sen University Guangdong Zhuhai519000 China School of Physics and Astronomy Yunnan University Yunnan Kunming650091 China Département de Physique Nucléaire et Corpusculaire Faculté de Sciences Université de Genève 24 Quai Ernest Ansermet Geneva1211 Switzerland Institute of Frontier and Interdisciplinary Science Shandon

In this work we try to search for signals generated by ultra-heavy dark matter at the Large High Altitude Air Shower Observatory (LHAASO) data. We look for possible gamma-ray by dark matter annihilation or decay from 16 dwarf spheroidal galaxies in the field of view of LHAASO. Dwarf spheroidal galaxies are among the most promising targets for indirect detection of dark matter which have low fluxes of astrophysical γ-ray background while large amount of dark matter. By analyzing more than 700 days observational data at LHAASO, no significant dark matter signal from 1 TeV to 1 EeV is detected. Accordingly we derive the most stringent constraints on the ultra-heavy dark matter annihilation cross-section up to EeV. The constraints on the lifetime of dark matter in decay mode are also derived. © 2024, CC BY.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Optimization of performance of the KM2A full array using the Crab Nebula

arXiv

引用

arXiv 2024年

作者： Cao, Zhen Aharonian, F. An, Q. Axikegu Bai, Y.X. Bao, Y.W. Bastieri, D. Bi, X.J. Bi, Y.J. Cai, J.T. Cao, Q. Cao, W.Y. Cao, Zhe Chang, J. Chang, J.F. Chen, A.M. Chen, E.S. Chen, Liang Chen, Lin Chen, Long Chen, M.J. Chen, M.L. Chen, Q.H. Chen, S.H. Chen, S.Z. Chen, T.L. Chen, Y. Cheng, N. Cheng, Y.D. Cui, M.Y. Cui, S.W. Cui, X.H. Cui, Y.D. Dai, B.Z. Dai, H.L. Dai, Z.G. Danzengluobu della Volpe, D. Dong, X.Q. Duan, K.K. Fan, J.H. Fan, Y.Z. Fang, J. Fang, K. Feng, C.F. Feng, L. Feng, S.H. Feng, X.T. Feng, Y.L. Gabici, S. Gao, B. Gao, C.D. Gao, L.Q. Gao, Q. Gao, W. Gao, W.K. Ge, M.M. Geng, L.S. Giacinti, G. Gong, G.H. Gou, Q.B. Gu, M.H. Guo, F.L. Guo, X.L. Guo, Y.Q. Guo, Y.Y. Han, Y.A. He, H.H. He, H.N. He, J.Y. He, X.B. He, Y. Heller, M. Hor, Y.K. Hou, B.W. Hou, C. Hou, X. Hu, H.B. Hu, Q. Hu, S.C. Huang, D.H. Huang, T.Q. Huang, W.J. Huang, X.T. Huang, X.Y. Huang, Y. Huang, Z.C. Ji, X.L. Jia, H.Y. Jia, K. Jiang, K. Jiang, X.W. Jiang, Z.J. Jin, M. Kang, M.M. Ke, T. Kuleshov, D. Kurinov, K. Li, B.B. Li, Cheng Li, Cong Li, D. Li, F. Li, H.B. Li, H.C. Li, H.Y. Li, J. Li, Jian Li, Jie Li, K. Li, W.L. Li, W.L. Li, X.R. Li, Xin Li, Y.Z. Li, Zhe Li, Zhuo Liang, E.W. Liang, Y.F. Lin, S.J. Liu, B. Liu, C. Liu, D. Liu, H. Liu, H.D. Liu, J. Liu, J.L. Liu, J.Y. Liu, M.Y. Liu, R.Y. Liu, S.M. Liu, W. Liu, Y. Liu, Y.N. Lu, R. Luo, Q. Lv, H.K. Ma, B.Q. Ma, L.L. Ma, X.H. Mao, J.R. Min, Z. Mitthumsiri, W. Mu, H.J. Nan, Y.C. Neronov, A. Ou, Z.W. Pang, B.Y. Pattarakijwanich, P. Pei, Z.Y. Qi, M.Y. Qi, Y.Q. Qiao, B.Q. Qin, J.J. Ruffolo, D. Sáiz, A. Semikoz, D. Shao, C.Y. Shao, L. Shchegolev, O. Sheng, X.D. Shu, F.W. Song, H.C. Stenkin, Yu.V. Stepanov, V. Su, Y. Sun, Q.N. Sun, X.N. Sun, Z.B. Tam, P.H.T. Tang, Q.W. Tang, Z.B. Key Laboratory of Particle Astrophyics Experimental Physics Division Computing Center Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China Tianfu Cosmic Ray Research Center Sichuan Chengdu610000 China Dublin Institute for Advanced Studies 31 Fitzwilliam Place 2 Dublin Ireland Max-Planck-Institut for Nuclear Physics P.O. Box 103980 Heidelberg69029 Germany State Key Laboratory of Particle Detection and Electronics China University of Science and Technology of China Anhui Hefei230026 China School of Physical Science and Technology School of Information Science and Technology Southwest Jiaotong University Sichuan Chengdu610031 China School of Astronomy and Space Science Nanjing University Jiangsu Nanjing210023 China Center for Astrophysics Guangzhou University Guangdong Guangzhou510006 China Hebei Normal University Hebei Shijiazhuang050024 China Key Laboratory of Dark Matter and Space Astronomy Key Laboratory of Radio Astronomy Purple Mountain Observatory Chinese Academy of Sciences Jiangsu Nanjing210023 China Tsung-Dao Lee Institute School of Physics and Astronomy Shanghai Jiao Tong University Shanghai200240 China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai200030 China Key Laboratory of Cosmic Rays Tibet University Ministry of Education Tibet Lhasa850000 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China Sun Yat-sen University Zhuhai519000 China Guangdong Guangzhou510275 China School of Physics and Astronomy Yunnan University Yunnan Kunming650091 China Département de Physique Nucléaire et Corpusculaire Faculté de Sciences Université de Genève 24 Quai Ernest Ansermet Geneva1211 Switzerland Institute of Frontier and Interdisciplinary Science Shandong University Shandong Qingdao266237 China APC Universit'e Paris Cit

The full array of the Large High Altitude Air Shower Observatory (LHAASO) has been in operation since July 2021. For its kilometer-square array (KM2A), we have optimized the selection criteria for very high and ultra-high energy γ-rays, using the data collected from August 2021 to August 2022, resulting in an improvement on significance of about 15% compared with previous cuts. With the implementation of these new selection criteria, the angular resolution is also significantly improved by approximately 10% at tens of TeV. Other aspects of the full KM2A array performance, such as the pointing error are also calibrated using the Crab Nebula. The resulting energy spectrum of the Crab Nebula in the energy range of 10-1000 TeV can be well fitted by a log-parabola model, which is consistent with the previous results from LHAASO and other experiments. © 2024, CC BY.

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

Adaptive NMS: Refining pedestrian detection in a crowd

arXiv

引用

arXiv 2019年

作者： Liu, Songtao Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density;(2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors;and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive unimodal cost volume filtering for deep stereo matching

arXiv

引用

arXiv 2019年

作者： Zhang, Youmin Chen, Yimin Bai, Xiao Yu, Suihanjin Yu, Kun Li, Zhiwei Yang, Kuiyuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China DeepMotion

state-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained. In this paper, we propose to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities. In addition, variances of the unimodal distributions for each pixel are estimated to explicitly model matching uncertainty under different contexts. The proposed architecture achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks. In particular, our method ranked the 1st place of KITTI 2012 evaluation and the 4th place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are available at: https://***/DeepMotionAIResearch/ DenseMatchingBenchmark. Copyright © 2019, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

STS MICCAI 2023 Challenge: Grand challenge on 2D and 3D semi-supervised tooth segmentation

arXiv

引用

arXiv 2024年

作者： Wang, Yaqi Zhang, Yifan Chen, Xiaodiao Wang, Shuai Qian, Dahong Ye, Fan Xu, Feng Zhang, Hongyuan Zhang, Qianni Wu, Chengyu Li, Yunxiang Cui, Weiwei Luo, Shan Wang, Chengkai Li, Tianhao Liu, Yi Feng, Xiang Zhou, Huiyu Liu, Dongyun Wang, Qixuan Lin, Zhouhao Song, Wei Li, Yuanlin Wang, Bing Wang, Chunshi Chen, Qiupu Li, Mingqian College of Media Engineering Communication University of Zhejiang Hangzhou China State Key Laboratory of Oral Diseases National Clinical Research Center for Oral Diseases West China Hospital of Stomatology Sichuan University Chengdu China Lishui University School of Medicine Hangzhou Geriatric Stomatology Hospital Hangzhou Dental Hospital Group Hangzhou China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Suzhou Research Institute of Shandong University Suzhou China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Medical School Shenzhen University Shenzhen China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Department of Mechanical Electrical and Information Engineering Shandong University Weihai China School of Management Hangzhou Dianzi University Hangzhou China Department of Stomatology Sichuan Provincial People's Hospital University of Electronic Science and Technology of China Chengdu China School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Zeta Technology Co. Ltd. No. 1158 Zhangdong Road Pudong New Area Shanghai China China Academy of Information and Communications Technology Beijing China HangZhou Dianzi University Xiasha Higher Education Zone Hangzhou China Southeast University Sipailou Xuanwu District Nanjing China Shanghai Ninth People's Hospital Shanghai Jiao Tong University School of Medicine Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology Changchun University of Science and Technology Changchun China School of Artificial Intelligence Guilin University of Electronic Technology Guilin China University of Science and Technology of China Hefei China Hefei Institutes of Physical Science Chinese Academy of Sciences No. 350 Shushan

Computer-aided design (CAD) tools are increasingly popular in modern dental practice, particularly for treatment planning or comprehensive prognosis evaluation. In particular, the 2D panoramic X-ray image efficiently detects invisible caries, impacted teeth and supernumerary teeth in children, while the 3D dental cone beam computed tomography (CBCT) is widely used in orthodontics and endodontics due to its low radiation dose. However, there is no open-access 2D public dataset for children's teeth and no open 3D dental CBCT dataset, which limits the development of automatic algorithms for segmenting teeth and analyzing diseases. The Semi-supervised Teeth Segmentation (STS) Challenge, a pioneering event in tooth segmentation, was held as a part of the MICCAI 2023 ToothFairy Workshop on the Alibaba Tianchi platform. This challenge aims to investigate effective semi-supervised tooth segmentation algorithms to advance the field of dentistry. In this challenge, we provide two modalities including the 2D panoramic X-ray images and the 3D CBCT tooth volumes. In Task 1, the goal was to segment tooth regions in panoramic X-ray images of both adult and pediatric teeth. Task 2 involved segmenting tooth sections using CBCT volumes. Limited labelled images with mostly unlabelled ones were provided in this challenge prompt using semi-supervised algorithms for training. In the preliminary round, the challenge received registration and result submission by 434 teams, with 64 advancing to the final round. This paper summarizes the diverse methods employed by the top-ranking teams in the STS MICCAI 2023 Challenge. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Coherent H ∞ control for Markovian jump linear quantum systems

引用

IFAC-PapersOnLine 2020年第2期53卷 269-274页

作者： Yanan Liu Daoyi Dong Ian R. Petersen Qing Gao Steven X. Ding Hidehiro Yonezawa School of Engineering and Information Technology University of New South Wales Canberra ACT 2600 Australia Center for Quantum Computation and Communication Technology Australian Research Council Canberra ACT 2600 Australia Institute for Automatic Control and Complex Systems (AKS) University of Duisburg-Essen. 47057 Duisburg Germany Research School of Electrical Energy and Materials Engineering The Australian National University Canberra ACT 2601 Australia School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment Beijing and also with Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China

The purpose of this paper is to design a coherent feedback controller for a Markovian jump linear quantum system suffering from a fault signal. The control objective is to bound the effect of the disturbance input on the output for the time-varying quantum system. We prove the relation between the H ∞ control problem, the dissipation properties, and the solutions of Riccati differential equations, by which the H ∞ controller of the Markovian jump linear quantum system is given by the solutions of Linear Matrix Inequalities (LMIs).

关键词： Coherent quantum feedback H∞ control fault-tolerant control Markovian jump linear quantum systems

来源：评论

学校读者我要写书评

暂无评论

Detection of data injection attack in industrial control system using long short term memory recurrent neural network

Detection of data injection attack in industrial control sys...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Wei Wang Yaobin Xie Lu Ren Xiaodong Zhu Rui Chang Qing Yin State Key Laboratory of Mathematic Engineering and Advanced Computing Zhengzhou China

In 2010, the outbreak of Stuxnet sounded a warning in the field of industrial ***. As the major attack form of Stuxnet, data injection attack is characterized by high concealment and great destructiveness. This paper proposes a new method to detect data injection attack in Industrial Control Systems (ICS), in which Long Short Term Memory Recurrent Neural Network (LSTM-RNN) is a temporal sequences predictor. We then use the Euclidean detector to identify attacks in a model of a chemical plant. With simulation and evaluation in Tennessee Eastman (TE) process, we show that this method is able to detect various types of data injection attacks.

关键词： Detectors Inductors Integrated circuits Temperature sensors Recurrent neural networks Security Logic gates

来源：评论

学校读者我要写书评

暂无评论

HPC AI500: A Benchmark Suite for HPC AI Systems 1st

HPC AI500: A Benchmark Suite for HPC AI Systems

引用

1st International Symposium on Benchmarking, Measuring, and Optimization, Bench 2018

作者： Jiang, Zihan Gao, Wanling Wang, Lei Xiong, Xingwang Zhang, Yuchen Wen, Xu Luo, Chunjie Ye, Hainan Lu, Xiaoyi Zhang, Yunquan Feng, Shengzhong Li, Kenli Xu, Weijia Zhan, Jianfeng State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Dover DE United States Beijing Academy of Frontier Sciences and Technology Beijing China State University of New York Buffalo United States Department of Computer Science and Engineering The Ohio State University Columbus United States National Supercomputing Center in Shenzhen Shenzhen China National Supercomputing Center in Changsha Changsha China National Supercomputing Center in Jinan Jinan China Texas Advanced Computing Center The Texas University at Austin Austin United States

ISBN: (纸本)9783030328122

In recent years, with the trend of applying deep learning (DL) in high performance scientific computing, the unique characteristics of emerging DL workloads in HPC raise great challenges in designing, implementing HPC AI systems. The community needs a new yard stick for evaluating the future HPC systems. In this paper, we propose HPC AI500—a benchmark suite for evaluating HPC systems that running scientific DL workloads. Covering the most representative scientific fields, each workload from HPC AI500 is based on real-world scientific DL applications. Currently, we choose 14 scientific DL benchmarks from perspectives of application scenarios, data sets, and software stack. We propose a set of metrics for comprehensively evaluating the HPC AI systems, considering both accuracy, performance as well as power and cost. We provide a scalable reference implementation of HPC AI500. The specification and source code are publicly available from http://***/HPCAI500/***. Meanwhile, the AI benchmark suites for datacenter, IoT, Edge are also released on the BenchCouncil web site. © 2019, Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing

KE-GAN: Knowledge Embedded Generative Adversarial Networks f...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Mengshi Qi Yunhong Wang Jie Qin Annan Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Inception Institute of Artificial Intelligence UAE

In recent years, scene parsing has captured increasing attention in computer vision. Previous works have demonstrated promising performance in this task. However, they mainly utilize holistic features, whilst neglecting the rich semantic knowledge and inter-object relationships in the scene. In addition, these methods usually require a large number of pixel-level annotations, which is too expensive in practice. In this paper, we propose a novel Knowledge Embedded Generative Adversarial Networks, dubbed as KE-GAN, to tackle the challenging problem in a semi-supervised fashion. KE-GAN captures semantic consistencies of different categories by devising a Knowledge Graph from the large-scale text corpus. In addition to readily-available unlabeled data, we generate synthetic images to unveil rich structural information underlying the images. Moreover, a pyramid architecture is incorporated into the discriminator to acquire multi-scale contextual information for better parsing results. Extensive experimental results on four standard benchmarks demonstrate that KE-GAN is capable of improving semantic consistencies and learning better representations for scene parsing, resulting in the state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：