检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Ximing Wang, Yang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China School of Computer Sci & Information Engineering Hefei University of Technology China

Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue, the existing PML methods basically recover the ground-truth labels by leveraging the ground-truth confidence of the candidate label, i.e., the likelihood of a candidate label being a ground-truth one. However, they neglect the information from non-candidate labels, which potentially contributes to the ground-truth label recovery. In this paper, we propose to recover the ground-truth labels, i.e., estimating the ground-truth confidences, from the label enrichment, composed of the relevance degrees of candidate labels and irrelevance degrees of non-candidate labels. Upon this observation, we further develop a novel two-stage PML method, namely Partial MultiLabel Learning with Label Enrichment-Recovery (PML3ER), where in the first stage, it estimates the label enrichment with unconstrained label propagation, then jointly learns the ground-truth confidence and multi-label predictor given the label enrichment. Experimental results validate that PML3ER outperforms the state-of-the-art PML methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

AR Navigation Application based on iOS Platform 2

AR Navigation Application based on iOS Platform

引用

2nd IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2019

作者： Wang, Xin Zhang, Risong Jilin University College of Computer Science and Technology Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9781728130668

In this paper, an Augmented Reality Navigation Application based on iOS platform is designed. This application is composed of five modules: the Location Module, the Digital Map Module, the Approximate Module, the Estimate Module and the AR Module. The Location Module requests current location via GPS in real-time and obtains the details of destination from map server. The Digital Map Module provides a Satellite Imagery View which superimposes navigation routes with marks such as current location, starting and destination. The Approximate module produced an approximation to fix the bias when converting the geographical coordinates between WGS-84 and GCJ-02 system. The Estimate Module produced a 3D position estimation according to a geographical coordinate provided by GPS or map server. This estimation will be used for placing the marks and routes in AR view. The AR Module provides an Augmented Reality scene superimposed destination and the route on a real-world background with a real-world scale. © 2019 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Error Formulas for Lagrange Projectors Determined by Cartesian Sets

引用

Journal of Systems Science & Complexity 2018年第4期31卷 1090-1102页

作者： LI Zhe ZHANG Shugong DONG Tian GONG Yihe School of Science Changchun University of Science and Technology Changchun 130022 China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun 130012 China School of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering (Ministry of Education) Jilin University Changchun 130012 China Northeast Electric Power University Jilin 132012 China School of Mathematics Jilin University Changchun 130012 China

This paper studies error formulas for Lagrange projectors determined by Cartesian sets. Cartesian sets are properly subgrids of tensor product grids. Given interpolated functions with all order continuous partial derivatives, the authors directly construct the good error formulas for Lagrange projectors determined by Cartesian sets. Owing to the special algebraic structure, such a good error formula is useful for error estimate.

关键词： Cartesian sets error formulas ideal interpolation multivariate polynomial interpolation

来源：评论

学校读者我要写书评

暂无评论

Job Placement Strategy with Opportunistic Resource Sharing for Distributed Deep Learning Clusters

Job Placement Strategy with Opportunistic Resource Sharing f...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Hongliang Li Ting Sun Xiang Li Haixiao Xu College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Changchun China High Performance Computing Center of Jilin University Changchun China

ISBN: (纸本)9781728176505

Distributed deep learning frameworks train large deep leaning workload with multiple training jobs on shared distributed GPU servers. There are new challenges when scheduling resources for these systems. Modern deep learning training jobs tend to consume large amount of GPU memory. A training job has an iterative nature that causes the memory usage fluctuate overtime. Jobs sharing a host may suffer from significant performance degradation caused by memory overload in runtime. Moreover, even without memory overloads, deep learning training jobs still experience different levels of performance interference when sharing a GPU device. This paper studies these two issues. We introduced an opportunistic memory sharing model to allocate resources for training jobs with time-varying memory requirements. Based on this model, we introduced an opportunistic Job Placement Problem (OJPP) for shared GPU clusters that seeks job placement configurations using minimum number of GPU devices and guarantees user-defined performance requirements. We proposed a greedy algorithm and a heuristic algorithm with computational complexities of $O(n\log n)$ and $O(n^{2}\log n)$, respectively, to solve the problem. Extensive experiments are conducted using a GPU cluster to verify the correctness, effectiveness, and the scalability of our approaches. The proposed approach achieved over 80% percent of the standalone performance, in term of average job completion time, with less than 30% extra resources consumption.

关键词： Training Deep learning Performance evaluation Greedy algorithms High performance computing Heuristic algorithms computational modeling

来源：评论

学校读者我要写书评

暂无评论

Joint optimization QoS and security of wireless communication networks 7

Joint optimization QoS and security of wireless communicatio...

引用

7th International Conference on Information Technology: IoT and Smart City, ICIT 2019

作者： Su, Xiaochun Liu, Yanheng Wan, Jian College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation Jilin University Changchun130012 China Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9781450376631

Currently, security and quality of service (QoS) are critical for any network. The main purpose of security mechanisms is to provide identity authentication, protect information, and ensure that the received information is not tampered with;the aim of QoS is to provide better network communication services. Security and QoS are not independent of each other. The security mechanism affects QoS and vice versa. Both QoS and security pose resource management problems and are conflicting when resources are limited. QoS requires security mechanisms to ensure proper allocation and service cost, and an inappropriate security mechanism will reduce the performance of the communication quality. Currently, numerous real-time, big data, and diverse applications and services have emerged. Moreover, the number of potential threats is expected to increase dramatically. Therefore, combining QoS and security is important. However, as they are difficult to model owing to their internal conflict, QoS and security are normally separated or optimized at a particular point using game theory. From the perspective of resource allocation, this study uses optimization method and considers security and QoS resource optimization by dividing resources into two categories: space (bandwidth) and time (delay). In order to harmonize the QoS and security, in this paper, the two conflicting terms "communication" and "security" are considered as two individual aspect. Furthermore, we construct a model wherein the joint utility is maximized by controlling the packet length. We formulate the utility functions of these two aspects with respect to the effective throughput. The results show that the presented optimization method enables a mobile node to adaptively select specific packet length based on the optimum curve. With the obtained packet length values, the joint utility reach to the maximum so that satisfactory communication quality can be realized without compromising the security, thereby improvin

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Motion deblur of QR code based on generative adversative network 2

Motion deblur of QR code based on generative adversative net...

引用

2nd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2019

作者： Wang, Benzhi Xu, Jingben Zhang, Junke Li, Guancheng Wang, Xin College of Computer Science and Technology Jilin University Changchun Jilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9781450372619

Aiming at the problem that the QR codes cannot be recognized due to factors such as motion blur caused by the hand tremor and environmental noise in the QR codes of the packaged product, this paper proposes an algorithm based on the Generative Adversative Network to remove QR codes motion blur. Compared with the traditional deblurring algorithm, this method eliminates the process of blur kernel estimation, directly restores the motion blurred image. Gradient L1 regularization is added on the basis of the traditional GAN, which enhances the edge features of the restored image and adds the perceptual loss term, so that the image generated by the generator is closer to the global structure of the target clear image. The results show that the generator can remove the blur and generate a QR code with high recognition rate. © 2019 ACM.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Copy-Move Forgery Detection Based on Interest Point and Local Search Algorithm

Copy-Move Forgery Detection Based on Interest Point and Loca...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Fang Mei Jing Lyu Yingda Lyu Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

Copy-move forgery detection mainly includes block-based and interest point-based methods, but both of them have shortcomings, such as weak resistance to affine transformations, weak ability to locate the forged region. To solve these problems, a novel algorithm is proposed in this paper, which involves two-stage search algorithm. The first stage takes image blocks as the search unit, and in the second stage, the forger region is searched at the pixel level. Experimental results demonstrate that the proposed method performants better compared to recent state-of-the-art methods.

关键词： Rail to rail outputs

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-based Non-Autoregressive Solver for Traveling Salesman Problems

arXiv

引用

arXiv 2023年

作者： Xiao, Yubin Wang, Di Li, Boyang Chen, Huanhuan Pang, Wei Wu, Xuan Li, Hao Xu, Dong Liang, Yanchun Zhou, You The Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China The Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly Nanyang Technological University 639798 Singapore The School of Computer Science and Engineering Nanyang Technological University 639798 Singapore The School of Computer Science University of Science & Technology of China Hefei230026 China The School of Mathematical and Computer Sciences Heriot-Watt University EdinburghEH14 4AS United Kingdom College of Computer National University of Defense Technology Hunan Changsha410073 China The Department of Electrical Engineering and Computer Science Bond Life Sciences Center University of Missouri Columbia United States The School of Computer Science Zhuhai College of Science and Technology Zhuhai519000 China

The Traveling Salesman Problem (TSP) is a well-known combinatorial optimization problem with broad real-world applications. Recently, neural networks have gained popularity in this research area because as shown in the literature, they provide strong heuristic solutions to TSPs. Compared to autoregressive neural approaches, non-autoregressive (NAR) networks exploit the inference parallelism to elevate inference speed but suffer from comparatively low solution quality. In this paper, we propose a novel NAR model named NAR4TSP, which incorporates a specially designed architecture and an enhanced reinforcement learning strategy. To the best of our knowledge, NAR4TSP is the first TSP solver that successfully combines RL and NAR networks. The key lies in the incorporation of NAR network output decoding into the training process. NAR4TSP efficiently represents TSP encoded information as rewards and seamlessly integrates it into reinforcement learning strategies, while maintaining consistent TSP sequence constraints during both training and testing phases. Experimental results on both synthetic and real-world TSPs demonstrate that NAR4TSP outperforms five state-of-the-art models in terms of solution quality, inference speed, and generalization to unseen scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Natural Image Matting by Refining Low-resolution Alpha Mattes

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Xianmin Ye Yihui Liang Mian Tan Fujian Feng Lin Wang Han Huang College of Data Science and Information Engineering Guizhou Minzu University Guiyang China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Key Laboratory of Pattern Recognition and Intelligent System and the College of Data Science and Information Engineering Guizhou Minzu University Guiyang China School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot (SCUT) MOE of China Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology Guangzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. Project page: https://***/yexianmin/HRAMR-Matting.

关键词： Feature extraction Image resolution Image color analysis Optimization Remote sensing Clustering algorithms Accuracy Visualization Transforms Training

来源：评论

学校读者我要写书评

暂无评论

Efficient reinforcement learning in continuous state and action spaces with Dyna and policy approximation

引用

Frontiers of Computer Science 2019年第1期13卷 106-126页

作者： Shan ZHONG Quan LIU Zongzhang ZHANG Qiming FU School of Computer Science and Technology Soochow UniversitySuzhou 215000China School of Computer Science and Engineering Changshu Institute of TechnologyChangshu 215500China Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency Suzhou University of Science and TechnologySuzhou 215006China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210000China College of Electronic &Information Engineering Suzhou University of Science and TechnologySuzhou 215000China

Dyna is an effective reinforcement learning (RL) approach that combines value function evaluation with model ***,existing works on Dyna mostly discuss only its efficiency in RL problems with discrete action *** paper proposes a novel Dyna variant,called Dyna-LSTD-PA,aiming to handle problems with continuous action ***-LSTD-PA stands for Dyna based on least-squares temporal difference (LSTD)and policy ***-LSTD-PA consists of two simultaneous,interacting *** learning process determines the probability distribution over action spaces using the Gaussian distribution;estimates the underlying value function,policy,and model by linear representation;and updates their parameter vectors online by LSTD(,t).The planning process updates the parameter vector of the value function again by using ofttine LSTD(2).Dyna-LSTD-PA also uses the Sherman-Morrison formula to improve the efficiency of LSTD(,t),and weights the parameter vector of the value function to bring the two processes ***,the global error bound is derived by considering approximation,estimation,and model ***,Dyna-LSTD-PA outperforms two representative methods in terms of convergence rate,success rate,and stability performance on four benchmark RL problems.

关键词： problem solving control methods heuristic search methods dynamic programming

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：