检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Liang, Yanhua Qin, Guihe Sun, Minghui Qin, Jun Yan, Jie Zhang, Zhonghan College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China School of Computer Science and Technology Changchun University of Science and Technology Changchun130012 China

Salient object detection in optical remote sensing images (RSI-SOD) aims to locate and extract visually discriminative objects or regions, which has attracted more and more attention from the community. The key challenge of RSI-SOD lies in the characteristics of optical RSIs, such as scale diversification of salient objects, irregular edges, and cluttered backgrounds. In this paper, we strive to embrace challenges towards effective and efficient RSI-SOD. To this end, we develop a framework, termed Adversarial Complementary Erasing Network (ACENet), which comprehensively mines discriminative features of different layers from foreground, background, local and global perspectives to perform robust and accurate saliency detection. Specifically, ACENet is a typical encoder-decoder structure that embeds Adversarial Erasing Synthesis Module (AESM) in multi-scale encoding features to fully explore more useful and complete representations. In AESM, we introduce Adversarial Discriminant Information Mining (ADIM) component to facilitate adaptive adjustment between salient features and background, further enabling more representative and strong integrity feature generation. Experimental results on three datasets prove that our ACENet significantly outperforms cutting-edge SOD models both qualitatively and quantitatively with a quick reasoning speed of 76 FPS. Code will be available at https://***/Liangyh18/ACENet. © 2023, The Authors. All rights reserved.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Understanding the Runtime Overheads of Deep Learning Inference on Edge Devices

Understanding the Runtime Overheads of Deep Learning Inferen...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Xiu Ma Guangli Li Lei Liu Huaxiao Liu Xiaobing Feng College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

With the growing ubiquity of the Internet of Things, in-the-edge inference of deep neural network models has been a major driver for promoting the widespread use of intelligent applications. As model inference characteristics are crucial for optimizing and deploying deep neural networks on hardware platforms, many studies focus on analyzing the performance of neural networks such as latency, accuracy, throughput, and energy consumption. However, few existing works have ever discussed the runtime overheads hidden in neural network inference, despite the overheads are non-negligible for edge applications. The lack of in-depth analysis of the overheads hinders the understanding of how hardware designs and model structures impact on-device inference performance. In this paper, we characterize the runtime overheads of deep learning inference on representative edge devices by leveraging state-of-the-art neural network models, performing a systematical analysis from the perspective of end-to-end performance, hardware platforms, memory bandwidth, and neural network model structures. Based on experimental results, the crucial insights are offered to facilitate the design and configure of resource-efficient networks and pick appropriate models on the specific platform, which provides a comprehensive view of runtime overheads of in-the- edge neural network inference for architects and developers.

关键词： Deep learning Performance evaluation Analytical models Runtime Roads Neural networks Throughput

来源：评论

学校读者我要写书评

暂无评论

Image annotation refinement using dynamic weighted voting based on mutual information

Journal of Software

引用

Journal of Software 2011年第11 SPEC. ISSUE期6卷 2239-2246页

作者： Song, Haiyu Li, Xiongfei Wang, Pengjie Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Computer Graphics and Image Processing Dalian Nationalities University Dalian China State Key Laboratory of CAD and CG Zhejiang University Hangzhou China

Automatic image annotation is a promising solution to narrow the semantic gap between low-level content and high-level semantic concept, which has been an active research area in the fields of image retrieval, pattern recognition, and machine learning. However, even the most dedicated annotation algorithms are often unsatisfactory. Image annotation refinement has attracted much more attention recently. In this paper, a novel refinement algorithm using dynamic voting based on mutual information is proposed. Unlike the traditional refinement algorithm, the proposed algorithm adopts dynamic weighted voting to measure the dependence between the candidate annotations, which not only permits that the annotations with higher probabilities deny the annotations with lower probabilities, but also permits that the annotations with lower probabilities deny the annotations with higher probabilities. The proposed refinement algorithm adopts progressive method instead of iterative, which can significantly decrease the time cost of refining annotations. In order to further improve efficiency without sacrificing precision, we propose the block-based normalized cut algorithm to segment image. Experiments conducted on standard Washington Ground Truth Image Database demonstrate the effectiveness and efficiency of our proposed approach for refining image annotations. © 2011 ACADEMY PUBLISHER.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

RiWalk: Fast structural node embedding via role identification

arXiv

引用

arXiv 2019年

作者： Ma, Xuewei Qin, Geng Qiu, Zhiyang Zheng, Mingxin Wang, Zhe College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

Nodes performing different functions in a network have different roles, and these roles can be gleaned from the structure of the network. Learning latent representations for the roles of nodes helps to understand the network and to transfer knowledge across networks. However, most existing structural embedding approaches suffer from high computation and space cost or rely on heuristic feature engineering. Here we propose RiWalk, a flexible paradigm for learning structural node representations. It decouples the structural embedding problem into a role identification procedure and a network embedding procedure. Through role identification, rooted kernels with structural dependencies kept are built to better integrate network embedding methods. To demonstrate the effectiveness of RiWalk, we develop two different role identification methods named RiWalk-SP and RiWalk-WL respectively and employ random walk based network embedding methods. Experiments on within-network classification tasks show that our proposed algorithms achieve comparable performance with other baselines while being an order of magnitude more efficient. Besides, we also conduct across-network role classification tasks. The results show potential of structural embeddings in transfer learning. RiWalk is also scalable, making it capable of capturing structural roles in massive networks. Copyright © 2019, The Authors. All rights reserved.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Structure- and Logic-Aware Heterogeneous Graph Learning for Recommendation

Structure- and Logic-Aware Heterogeneous Graph Learning for ...

引用

International Conference on Data engineering

作者： Anchen Li Bo Yang Huan Huo Farookh Khadeer Hussain Guandong Xu College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Aalto University Espoo Finland School of Computer Science University of Technology Sydney Sydney Australia Education University of Hong Kong Hong Kong China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Recently, there has been a surge in recommendations based on heterogeneous information networks (HINs), attributed to their ability to integrate complex and rich semantics. Despite this advancement, most HIN-based recommenders overlook two critical aspects. First, they often fail to consider HIN's heterophily nature, hindering the capture of non-local structures in HINs. Second, most methods lack the capability for logical reasoning. In this paper, we propose a novel structure- and logic-aware heterogeneous graph learning framework for recommender systems (SLHRec). Our SLHRec contains a structure-aware module and a logic-aware module. The former uses network geometry to construct non-local neighborhoods for nodes in HINs, and then introduces a graph neural network to integrate constructed neighbors for modeling the heterophily of HINs. The logic-aware module uses the Markov logic network (MLN) to infuse logic rules into heterogeneous graph learning, thereby boosting logic reasoning in recommendations. Furthermore, we utilize contrastive learning to model cooperative signals between modules, enabling them to complement each other. In the prediction stage, both modules contribute to generating recommendations. Compared with several strong recommender baselines, our SLHRec achieves superior performance on four real-world datasets.

关键词： Geometry Semantics Contrastive learning Data engineering Boosting Cognition Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling and Mining Spatiotemporal Social Contact of Metapopulation from Heterogeneous Data

Modeling and Mining Spatiotemporal Social Contact of Metapop...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Bo Yang Hongbin Pei Hechang Chen Jiming Liu Shang Xia School of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Department of Computer Science Hong Kong Baptist University Hong Kong National Institute of Parasitic Diseases Chinese CDC Shanghai China

ISBN: (纸本)9781479943012

During an epidemic, the spatial, temporal and demographical patterns of disease transmission are determined by multiple factors. Besides the physiological properties of pathogenes and hosts, the social contacts of host population, which characterize individuals' reciprocal exposures of infection in view of demographical structures and various social activities, are also pivotal to understand and further predict the prevalence of infectious diseases. The means of measuring social contacts will dominate the extent how precisely we can forecast the dynamics of infections in the real world. Most current works focus their efforts on modeling the spatial patterns of static social contacts. In this work, we address the problem on how to characterize and measure dynamical social contacts during an epidemic from a novel perspective. We propose an epidemic-model-based tensor deconvolution framework to address this issue, in which the spatiotemporal patterns of social contacts are represented by the factors of tensors, which can be discovered by a tensor deconvolution procedure with an integration of epidemic models from rich types of data, mainly including heterogeneous outbreak surveillance, social-demographic census and physiological data from medical reports. Taking SIR model as a case study, the efficacy of the proposed method is theoretically analyzed and empirically validated through a set of rigorous experiments on both synthetic and real-world data.

关键词： educational institutions Diseases Sociology Statistics Tensile stress Surveillance Data models

来源：评论

学校读者我要写书评

暂无评论

Adaptive feature selection and extraction approaches for image retrieval based on region

引用

Journal of Multimedia 2010年第1期5卷 85-92页

Image retrieval based on region is one of the most promising and active research directions in recent year's CBIR, while region segmentation, feature selection and feature extraction of region are key issues. However, the existing approaches always adopt a uniform approach of segmentation and feature extraction for all images in the same system. In this paper, we propose adaptive image segmentation and feature extraction approach according to different category image for image retrieval system. To improve performance, we propose adaptive segmentation approach according to different category image. Textured image is segmented by Gaussian Mixture Models (GMM), while non-textured image is segmented by our proposed block-based normalized cut. To accurately describe feature of region, we propose weight assignment method for centroid pixel and its neighbor by convolution with normal distribution when image segmentation by GMM. To improve generalization, we propose adaptive number of Fourier descriptors of shape signature which depends on the energy distribution of Fourier descriptors, instead of fixed number by experience. To simply and efficiently describe the spatial relationships of multi-object or multi-region in same image, we apply simplified topological relationships. The experiments demonstrate that proposed approaches are superior to the traditional approaches. © 2010 ACADEMY PUBLISHER.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

PBCounter: Weighted Model Counting on Pseudo-Boolean Formulas

arXiv

引用

arXiv 2023年

作者： Lai, Yong Xu, Zhenghang Yin, Minghao College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China School of Computer Science and Information Technology Northeast Normal University Changchun130017 China

In Weighted Model Counting (WMC), we assign weights to literals and compute the sum of the weights of the models of a given propositional formula where the weight of an assignment is the product of the weights of its literals. The current WMC solvers work on Conjunctive Normal Form (CNF) formulas. However, CNF is not a natural representation for human-being in many applications. Motivated by the stronger expressive power of pseudo-Boolean (PB) formulas than CNF, we propose to perform WMC on PB formulas. Based on a recent dynamic programming algorithm framework called ADDMC for WMC, we implement a weighted PB counting tool PBCounter. We compare PBCounter with the state-of-the-art weighted model counters SharpSAT-TD, ExactMC, D4, and ADDMC, where the latter tools work on CNF with encoding methods that convert PB constraints into a CNF formula. The experiments on three domains of benchmarks show that PBCounter is superior to the model counters on CNF formulas. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Efficient and Privacy-Preserving Eclipse Query Over Encrypted Data

Efficient and Privacy-Preserving Eclipse Query Over Encrypte...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Weiyu Song Yonggang Zhang Lili Sun Yandong Zheng Rongxing Lu College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China State Key Laboratory of Integrated Services Networks Xidian University Xi'an China Faculty of Computer Science University of New Brunswick Fredericton Canada

As the mobile Internet grows rapidly, location-based services (LBSs) are widely applied in the tourism and transportation fields. To fully mine the data collected, location service providers (LSPs) intend to offer various query services to users, which include eclipse query. The eclipse query can generalize nearest neighbor queries and skyline queries and allow users to set more rough and customizable preference ranges. In addition, with the boom of cloud computing, more and more LSPs hope to leverage the cloud to offer better query services. Given that the data could potentially contain confidential information, the data are required to be encrypted prior to outsourcing them. Therefore, eclipse queries need to be executed on the ciphertext. Although several schemes for eclipse queries have been proposed in existing works, they have little focus on privacy issues. To address this issue, we propose an efficient and privacy-preserving scheme for eclipse queries (EPEQ) in this paper. First, we develop a MinValue tree to construct an index for the dataset. Then, by utilizing the MinValue tree and a symmetric homomorphic encryption technique, we design a secure minimum value comparison protocol to obtain a skyline data and a secure undominated data acquisition protocol to obtain the data not skyline dominated by the skyline data. After that, we present our scheme. We analyze the security of the EPEQ scheme and perform experimental evaluations, demonstrating the security and efficiency of our EPEQ scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Task Processing Efficiency Improvement Scheme Based on Cloud-Edge Architecture in Dense Computing Environments

SSRN

引用

SSRN 2022年

作者： Feng, Jiahui Qi, Jingze Liu, Yuanning Liu, Zhen College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Graduate School of Engineering Nagasaki Institute of Applied Science 536 Aba-machi Nagasaki851-0193 Japan

As cloud-edge architecture combines low latency and high-performance computing, it has a wider range of application scenarios. Considering that, how to reasonably allocate tasks to the edge cloud or the central cloud and how to select appropriate virtual machines (VMs) for tasks are two key aspects affecting the efficiency of cloud-edge architecture. For the former, the ARDT algorithm is proposed, which dynamically adjusts the optimal threshold by predicting the number of real-time edge-end devices. For the latter, we design the DBMR algorithm based on the Max-Fit algorithm, in which we propose a structure of blocking to reduce the time complexity of the original algorithm from O(n2) to O(n(n-m)). Experimental results show that the ARDT-DBMR algorithm optimizes the average processing time and task failure rate by 30%-40% compared with the baseline algorithms and other advanced algorithms and significantly improves the problem of abnormal fluctuations in VM utilization in dense computing environments. © 2022, The Authors. All rights reserved.

关键词： Virtual machine

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：