检索结果-内蒙古大学图书馆

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ding, Zixiang Chen, Yaran Li, Nannan Zhao, Dongbin Chen, C.L. Philip State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Computer Science & Engineering South China University of Technology Guangdong Guangzhou510006 China College of Navigation Dalian Maritime University Dalian116026 China

Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Network (BCNN), as the search space for amazing efficiency improvement. BCNN reuses the topologies of cells in the convolution block so that BNAS can employ few cells for efficient search. Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology. However, BNAS suffers some drawbacks: 1) insufficient representation diversity for feature fusion and enhancement and 2) time consumption of knowledge embedding design by human experts. This paper proposes Stacked BNAS, whose search space is a developed broad scalable architecture named Stacked BCNN, with better performance than BNAS. On the one hand, Stacked BCNN treats mini BCNN as a basic block to preserve comprehensive representation and deliver powerful feature extraction ability. For multi-scale feature enhancement, each mini BCNN feeds the outputs of deep and broad cells to the enhancement cell. For multi-scale feature fusion, each mini BCNN feeds the outputs of deep, broad and enhancement cells to the output node. On the other hand, Knowledge Embedding Search (KES) is proposed to learn appropriate knowledge embeddings in a differentiable way. Moreover, the basic unit of KES is an over-parameterized knowledge embedding module that consists of all possible candidate knowledge embeddings. Experimental results show that 1) Stacked BNAS obtains better performance than BNAS-v2 on both CIFAR-10 and ImageNet, 2) the proposed KES algorithm contributes to reducing the parameters of the learned architecture with satisfactory performance, and 3) Stacked BNAS delivers a state-of-the-art efficiency of 0.02 GPU days. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

Single-shot fringe projection profilometry based on deep learning and computer graphics

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Fanzhou Wang, Chenxing Guan, Qingze School of Automation Southeast University 2# Sipailou Xuanwu Nanjing210096 China Key laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Department of Computer Science University College London Gower St Bloomsbury LondonWC1E 6BT United Kingdom

Multiple works have applied deep learning to fringe projection profilometry (FPP) in recent years. However, to obtain a large amount of data from actual systems for training is still a tricky problem, and moreover, the network design and optimization still worth exploring. In this paper, we introduce computer graphics to build virtual FPP systems in order to generate the desired datasets conveniently and simply. The way of constructing a virtual FPP system is described in detail firstly, and then some key factors to set the virtual FPP system much close to the reality are analyzed. With the aim of accurately estimating the depth image from only one fringe image, we also design a new loss function to enhance the quality of the overall and detailed information restored. And two representative networks, U-Net and pix2pix, are compared in multiple aspects. The real experiments prove the good accuracy and generalization of the network trained by the data from our virtual systems and the designed loss, implying the potential of our method for applications. Copyright © 2021, The Authors. All rights reserved.

关键词： computer graphics

Correction to: Comparative analysis of metaheuristic load balancing algorithms for efficient load balancing in cloud computing

学校读者我要写书评

暂无评论

Journal of Cloud Computing 2025年第1期14卷 1-1页

作者： Zhou, Jincheng Lilhore, Umesh Kumar M, Poongodi Hai, Tao Simaiya, Sarita Abang Jawawi, Dayang Norhayati Alsekait, Deema Mohammed Ahuja, Sachin Biamba, Cresantus Hamdi, Mounir School of Computer and Information and Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Qiannan Normal University for Nationalities Duyun China Department of Computer Science and Engineering Chandigarh University Mohali India College of Science and Engineering Hamad Bin Khalifa University Qatar Foundation Doha Qatar School of Computing Faculty of Engineering Universiti Teknologi Malaysia (UTM) Johor Malaysia Department of Computer Science and Information Technology Princess Nourah Bint Abdul Rahman University Applied College Riyadh Saudi Arabia Department of Culture Studies Religious Studies and Educational Sciences University of Gävle Gävle Sweden

Left ventricle contouring in cardiac images based on deep reinforcement learning

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Yin, Sixing Han, Yameng Pan, Judong Wang, Yining Li, Shufang Yu, F. Richard Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China University of California San Francisco San FranciscoCA94117 United States State Key Laboratory of Complex Severe and Rare Diseases Chinese Academy of Medical Sciences Peking Union Medical College Beijing100730 China The Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agent’s movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agent’s landing spot (or coordinate of its initial position on a cardiac image). The experiment results show that the coordinate of the generated landing spot is sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model even with limited training set. © 2021, CC BY.

关键词： Reinforcement learning

A reinforcement-learning-based energy-efficient framework for multi-task video analytics pipeline

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Yingying Dong, Mingzhi Wang, Yujiang Feng, Da Lv, Qin Dick, Robert P. Li, Dongsheng Lu, Tun Gu, Ning Shang, Li School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China Department of Computing Imperial College London London United Kingdom Software Service Company Limited Beijing China University of Colorado Boulder BoulderCO United States Department of Electrical Engineering and Computer Science College of Engineering University of Michigan Ann ArborMI United States Microsoft Research Asia Shanghai China School of Computer Science Fudan University Shanghai China

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energy-constrained applications. Motivated by the observation of high and variable spatial redundancy and temporal dynamics in video data streams, we design and evaluate an adaptive-resolution optimization framework to minimize the energy use of multitask video analytics pipelines. Instead of heuristically tuning the input data resolution of individual tasks, our framework utilizes deep reinforcement learning to dynamically govern the input resolution and computation of the entire video analytics pipeline. By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency. Governed by reinforcement learning, optical flow is incorporated into the framework to minimize unnecessary spatio-temporal redundancy that leads to re-computation, while preserving accuracy. The proposed framework is applied to video instance segmentation which is one of the most challenging computer vision tasks, and achieves better energy efficiency than all baseline methods of similar accuracy on the YouTube-VIS dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

Motion Planning for Heterogeneous Unmanned systems under Partial Observation from UAV

学校读者我要写书评

暂无评论

Motion Planning for Heterogeneous Unmanned Systems under Par...

2020 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Ci Chen Yuanfang Wan Baowei Li Chen Wang Guangming Xie Huanyu Jiang College of Biosystems Engineering and Food Science Zhejiang University Hangzhou China Southern University of Science and Technology Shenzhen China The State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

For heterogeneous unmanned systems composed of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), using UAVs serve as eyes to assist UGVs in motion planning is a promising research direction due to the UAVs' vast view scope. However, its limitations on flight altitude prevent the UAVs from observing the global map. Thus motion planning in the local map becomes a Partially Observable Markov Decision Process (POMDP) problem. This paper proposes a motion planning algorithm for heterogeneous unmanned systems under partial observation from UAV without reconstruction of global maps. Our algorithm consists of two parts designed for perception and decision-making, respectively. For the perception part, we propose the Grid Map Generation Network (GMGN), which is used to perceive scenes from UAV's perspective and classify the pathways and obstacles. For the decision-making part, we propose the Motion Command Generation Network (MCGN). Due to the addition of the memory mechanism, MCGN has planning and reasoning abilities under partial observation from UAVs. We evaluate our proposed algorithm by comparing it with baseline algorithms. The results show that our method effectively plans the motion of heterogeneous unmanned systems and achieves a relatively high success rate.

关键词： Decision making Markov processes Unmanned aerial vehicles Land vehicles Planning Classification algorithms Intelligent robots

REFUGE2 CHALLENGE: A TREASURE TROVE FOR MULTI-DIMENSION ANALYSIS AND EVALUATION IN GLAUCOMA SCREENING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fang, Huihui Li, Fei Wu, Junde Fu, Huazhu Sun, Xu Son, Jaemin Yu, Shuang Zhang, Menglu Yuan, Chenglang Bian, Cheng Lei, Baiying Zhao, Benjian Xu, Xinxing Li, Shaohua Fumero, Francisco Sigut, José Almubarak, Haidar Bazi, Yakoub Guo, Yuanhao Zhou, Yating Baid, Ujjwal Innani, Shubham Guo, Tianjiao Yang, Jie Orlando, José Ignacio Bogunović, Hrvoje Zhang, Xiulan Xu, Yanwu The REFUGE2 Challenge Australia State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-Sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Intelligent Healthcare Unit Baidu Inc. Beijing China The Institute of High Performance Computing Agency for Science Technology and Research Singapore Yatiris Group PLADEMA Institute CONICET UNICEN Tandil Argentina Christian Doppler Lab for Artificial Intelligence in Retina Department of Ophthalmology and Optometry Medical University of Vienna Vienna Austria VUNO Inc Seoul Korea Republic of Tencent HealthCare Tencent Shenzhen China Computer Vision Institute College of Computer Science and Software Engineering of Shenzhen University Shenzhen China School of Biomedical Engineering Health Science Center Shenzhen University China Xiaohe Healthcare ByteDance Guangdong Guangzhou510000 China School of Biomedical Engineering Shenzhen University China College of Computer Science & Software Engineering Shenzhen University China Department of Computer Science and Systems Engineering Universidad de La Laguna Spain Saudi Electronic University Saudi Arabia King Saud University Saudi Arabia Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China SGGS Institute of Engineering and Technology India Institute of Medical Robotics Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

With the rapid development of artificial intelligence (AI) in medical image processing, deep learning in color fundus photography (CFP) analysis is also evolving. Although there are some open-source, labeled datasets of CFPs in the ophthalmology community, large-scale datasets for screening only have labels of disease categories, and datasets with annotations of fundus structures are usually small in size. In addition, labeling standards are not uniform across datasets, and there is no clear information on the acquisition device. Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge-Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2). The REFUGE2 dataset contains 2000 color fundus images with annotations of glaucoma classification, optic disc/cup segmentation, as well as fovea localization. Meanwhile, the REFUGE2 challenge sets three sub-tasks of automatic glaucoma diagnosis and fundus structure analysis and provides an online evaluation framework. Based on the characteristics of multi-device and multi-quality data, some methods with strong generalizations are provided in the challenge to make the predictions more robust. This shows that REFUGE2 brings attention to the characteristics of real-world multi-domain data, bridging the gap between scientific research and clinical application. © 2022, CC BY-NC-ND.

关键词： Color

A New Atmospheric Dataset for GIIRS Sampled from ERA5 Using Shannon Entropy Method

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental Science 2021年第1期668卷

作者： Qi Zhang Yi Yu Weimin Zhang College of Meteorology and Oceanography National University of Defense Technology Changsha 410073 China College of Computer Science National University of Defense Technology Changsha 410073 China Key Laboratory of Software Engineering for Complex Systems Changsha 410073 China

Geostationary Interferometric Infrared Sounder (GIIRS) on board the new Chinese geostationary meteorological satellite Fengyun-4A is aimed to obtain three-dimensional atmospheric information regularly at the regional scale. Since the existing atmospheric datasets are global covered and they are not representative of the GIIRS detection area, a diverse and local representative atmospheric dataset is required for GIIRS in training transmittance parameterization scheme of fast radiative transfer model and retrieving atmospheric profiles. The new atmospheric dataset for GIIRS application in this paper is sampled from the European Centre for Medium-Range Weather Forecasts (ECMWF) fifth-generation reanalysis (ERA5) 2019 dataset using Shannon entropy sampling method. The new dataset demonstrates the feature of uniform distribution within multiple atmospheric variables' (i.e. atmospheric temperature, specific humidity, 2 meter temperature) variation ranges and GIIRS's spatial coverage. To address the issue derived from the climate difference and the varied vertical pressure structure of regions with great differences in topographic height, the study area is divided into six categories regarding of topographic height categories where atmospheric dataset are sampled separately. Seasonal variation is also taken into account in the process of sampling. Compared with the initial randomly sampled dataset, the atmospheric and 2 meter temperature in the new dataset demonstrate a higher level of uniformity within their variation ranges. The statistical results indicate that the differences between samples in the new dataset are enlarged, meanwhile, the new dataset well retains the statistical characteristics of the original ERA5 dataset. The new dataset has a potential in the study of the utility of GIIRS data in the numerical weather forecast.

关键词：

Fuzzy Rate Analysis of Operators and its Applications in Linear Spaces

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Zhang, Yijin Li, Honggang Jin, Maoming Lin, Zongbing Nanjing Changjiang Waterway Engineering Bureau China Key Lab of Intelligent Analysis and Decision on Complex Systems Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Pass College Chongqing Technology and Business University Chongqing401520 China Institute of Nonlinear Analysis Research Changjiang Normal University Chongqing400803 China School of Mathematics and Computer Science Panzhihua University Panzhihua617000 China

In this paper, a new concept, the fuzzy rate of an operator in linear spaces is proposed for the very first time. Some properties and basic principles of it are studied. Fuzzy rate of an operator B which is specific i... 详细信息

关键词： Membership functions