检索结果-内蒙古大学图书馆

Recent progress in semantic image segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Xiaolong Deng, Zhidong Yang, Yuhan State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science Tsinghua University Beijing100084 China Department of Economics and Management Tsinghua University Beijing100084 China

Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, upsample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Neural machine translation with explicit phrase alignment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Jiacheng Luan, Huanbo Sun, Maosong Zhai, FeiFei Xu, Jingfang Liu, Yang Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Sogou Inc. Beijing China

While neural machine translation (NMT) has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in NMT models leads to three problems: it is hard to (1) interpret the translation process, (2) impose lexical constraints, and (3) impose structural constraints. To alleviate these problems, we propose to introduce explicit phrase alignment into the translation process of arbitrary NMT models. The key idea is to build a search space similar to that of phrase-based statistical machine translation for NMT where phrase alignment is readily available. We design a new decoding algorithm that can easily impose lexical and structural constraints. Experiments show that our approach makes the translation process of NMT more interpretable without sacrificing translation quality. In addition, our approach achieves significant improvements in lexically and structurally constrained translation tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural machine translation

The Prediction of the Epidemic Trend of COVID-19 Using Neural Networks

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第5期53卷 857-862页

作者： Jing Yang Zhen Shen Xisong Dong Xiuqin Shang Wei Li Gang Xiong J. Yang is with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with College of Information Sciences & Technology Beijing University of Chemical Technology Beijing 100029 China. Z. Shen is with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with the Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao Shandong 266113 China. X. Dong X. Shang and W. Li are with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China. G. Xiong is with Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with the Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Dongguan Guangdong 523808 China.

In this paper, a BP neural network and an LSTM network are applied respectively to the prediction of Coronavirus Disease 2019 (COVID-19) in Wuhan, China and South Korea. The methods do not require specific theories of modelling and the predicted values can be obtained as long as the conventional parameters are set. The mean absolute percentage error (MAPE) of all the experiments are below 5% and the values of the determinable coefficient R are all larger than 0.9. The experiments show that the models can fit the actual values well and make relatively accurate predictions. As of March 29, 2020, the cumulative number of confirmed cases in Wuhan is expected to reach 50,068 using BP neural networks and 49,972 using LSTM network, respectively. As of April 13, 2020, the cumulative number of confirmed cases in South Korea is expected to reach 8,862 using BP neural networks and 8,716 using LSTM network, respectively. The models of neural networks are effective in predicting the trend of the COVID-19 epidemic, which is meaningful to prevent and control the epidemic.

关键词：

Hard-instance learning for quantum adiabatic prime factorization

学校读者我要写书评

暂无评论

Physical Review A 2022年第6期105卷 062455-062455页

作者： Jian Lin Zhengfeng Zhang Junping Zhang Xiaopeng Li State Key Laboratory of Surface Physics Institute of Nanoelectronics and Quantum Computing and Department of Physics Fudan University Shanghai 200433 China Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai 200433 China Shanghai Qi Zhi Institute Xuhui District Shanghai 200032 China Shanghai Research Center for Quantum Sciences Shanghai 201315 China

Prime factorization is a difficult problem with classical computing, whose exponential hardness is the foundation of Rivest-Shamir-Adleman cryptography. With programable quantum devices, adiabatic quantum computing has been proposed as a plausible approach to solve prime factorization, having promising advantage over classical computing. Here, we find there are certain hard instances that are consistently intractable for both classical simulated annealing and unconfigured adiabatic quantum computing (AQC). Aiming at an automated architecture for optimal configuration of quantum adiabatic factorization, we apply a deep reinforcement learning (RL) method to configure the AQC algorithm. By setting the success probability of the worst-case problem instances as the reward to RL, we show the AQC performance on the hard instances is dramatically improved by RL configuration. The success probability also becomes more evenly distributed over different problem instances, meaning the configured AQC is more stable as compared to the unconfigured case. Through a technique of transfer learning, we find prominent evidence that the framework of AQC configuration is scalable—the configured AQC as trained on five qubits remains working efficiently on nine qubits with a minimal amount of additional training cost.

关键词： Machine learning Quantum algorithms Quantum computation Quantum simulation

SkinFormer: Learning Statistical Texture Representation with Transformer for Skin Lesion Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Rongtao Wang, Changwei Zhang, Jiguang Xu, Shibiao Meng, Weiliang Zhang, Xiaopeng The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China CASIA Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China

Accurate skin lesion segmentation from dermoscopic images is of great importance for skin cancer diagnosis. However, automatic segmentation of melanoma remains a challenging task because it is difficult to incorporate useful texture representations into the learning process. Texture representations are not only related to the local structural information learned by CNN, but also include the global statistical texture information of the input image. In this paper, we propose a transFormer network (SkinFormer) that efficiently extracts and fuses statistical texture representation for Skin lesion segmentation. Specifically, to quantify the statistical texture of input features, a Kurtosis-guided Statistical Counting Operator is designed. We propose Statistical Texture Fusion Transformer and Statistical Texture Enhance Transformer with the help of Kurtosis-guided Statistical Counting Operator by utilizing the transformer’s global attention mechanism. The former fuses structural texture information and statistical texture information, and the latter enhances the statistical texture of multi-scale features. Extensive experiments on three publicly available skin lesion datasets validate that our SkinFormer outperforms other SOAT methods, and our method achieves 93.2% Dice score on ISIC 2018. It can be easy to extend SkinFormer to segment 3D images in the future. Our code is available at https://***/RongtaoXu/SkinFormer. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

Cyber-Physical -Social systems for Smart Cities: An Overview

学校读者我要写书评

暂无评论

Cyber-Physical -Social Systems for Smart Cities: An Overview

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Noreen Anwar Gang Xiong Wanze Lu Peijun Ye Hongxia Zhao Qinglai Wei The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation and with The Cloud Computing Center Chinese Academy of Sciences China School of Artificial Intelligence and Automation Beijing University of Technology Beijing China

Cyber-physical social systems (CPSS) include cyberspace, physical space, and social space. Since the introduction of CPSS, human relationships with machinery and the physical world have altered as a new paradigm. Recent estimates indicate that approximately 60 percent of the world's population will live in cities by 2030. Large, dense cities can be highly productive, innovative, and very green per capita, hence ideal for our future. However, the huge influx of new people poses enormous challenges to their administrations. Smart cities are becoming a reality, therefore, to achieve higher efficiency, optimum use of resources, management and to strengthen several features of modern towns, several elements of modern cities are automated and integrated into Information and Communications Technology (ICT). Cities and infrastructure are growing all over the world, in providing end-users with increased performance, comfort, visibility and convenience, the Smart Cities concept is critical. This paper will discuss smart cities and the CPSS concept intensively with some of its key technologies, challenges, and further development by using CPSS.

关键词： Smart cities Digital twin Sociology Information and communication technology Security Resource management Statistics

Convolutional Neural Networks with Gated Recurrent Connections

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Jianfeng Hu, Xiaolin the Computer Science Department University of Oxford Oxfordshire United Kingdom the Institute for Artificial Intelligence the State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100084 China

The convolutional neural network (CNN) has become a basic model for solving many computer vision problems. In recent years, a new class of CNNs, recurrent convolution neural network (RCNN), inspired by abundant recurrent connections in the visual systems of animals, was proposed. The critical element of RCNN is the recurrent convolutional layer (RCL), which incorporates recurrent connections between neurons in the standard convolutional layer. With increasing number of recurrent computations, the receptive fields (RFs) of neurons in RCL expand unboundedly, which is inconsistent with biological facts. We propose to modulate the RFs of neurons by introducing gates to the recurrent connections. The gates control the amount of context information inputting to the neurons and the neurons’ RFs therefore become adaptive. The resulting layer is called gated recurrent convolution layer (GRCL). Multiple GRCLs constitute a deep model called gated RCNN (GRCNN). The GRCNN was evaluated on several computer vision tasks including object recognition, scene text recognition and object detection, and obtained much better results than the RCNN. In addition, when combined with other adaptive RF techniques, the GRCNN demonstrated competitive performance to the state-of-the-art models on benchmark datasets for these tasks. The codes are released at https://***/Jianf-Wang/GRCNN. © 2021, CC BY.

关键词： Convolution

Feature Selection and Learning-Based Model for Uav Path Planning on Rough Terrains

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Ali, Hub Xiong, Gang Husnain, Haider Muhammad Tamir, Tariku Sinshaw Dong, Xisong Shen, Zhen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Qingdao Academy of Intelligent Industries Qingdao266109 China Chengdu610054 China

Path planning and obstacle avoidance in 3D terrain have been identified as a monumental challenge for a UAV in a variety of autonomous missions, such as disaster management and search and rescue operations. In large terrain areas, it’s a key problem for traditional approaches to search within the point-cloud maps to find a global path for a UAV considering the flight safety, maneuverability, weather constraints, and fuel cost. Hence, this paper proposes a trajectory planning technique for global and local path planning of a fixed-wing UAV above 3D terrain under static and dynamic constraints. For global path generation, a novel Feature Selection and Learning-based Model (FSLM) has been introduced to select the features of a point-cloud map and transform them into the feature set. The feature set is utilized by an improved A* planner with an extensive search area to deliver an optimal global path. The global path is assumed as the UAV's reference waypoints. The motion of the UAV on reference waypoints is simplified with two coordinates (R, d), where R is the cumulative distance covered by the UAV along the reference waypoints and d is its offset distance from the reference line segment in time t. For any local collision, offset trajectories are generated along with reference waypoints to avoid collision. Cost functions have been added so that the best global and local path can be chosen, taking into account altitude, weather, and fuel constraints. The simulation results show the performance of this approach in various complex terrains by considering weather and dynamic constraints, and the results are also compared to other 3D UAV path planning techniques. © 2022, The Authors. All rights reserved.

关键词： Motion planning

Auto-MatRegressor材料性能自动预测器:解放材料机器学习"调参师"

学校读者我要写书评

暂无评论

Science Bulletin 2023年第12期68卷 1259-1270,M0004页

作者：刘悦王双燕杨正伟 Maxim Avdeev 施思齐 School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China Zhejiang Laboratory Hangzhou 311100China Australian Nuclear Science and Technology Organisation Sydney 2232Australia School of Chemistry The University of SydneySydney 2006Australia

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材... 详细信息

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材料性能自动预测器,采集了60份文献公开数据集与60份标准数据集,基于此训练18种常用回归算法并获得其预测性能,定义与计算了27个刻画数据集特点的元特征,以此构建了一份蕴含建模经验的元数据集;同时,创建了表征数据集所属材料类型的类别树,将其嵌入基于距离的元学习算法,进一步耦合贝叶斯优化算法,实现领域知识和元数据协同驱动下的自动算法推荐和模型参数确定,实验结果表明,材料科学家仅需为新材料性能预测任务提供数据集,便可利用该预测器高效地构建具有与文献报道相当或更高预测精度的机器学习模型.

关键词：机器学习贝叶斯优化算法预测器材料科学家元数据参数寻优预测性能材料性能