检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Impact of temperature and relative humidity on the transmission of COVID-19: A modeling study in China and the United States

arXiv

引用

arXiv 2020年

作者： Wang, Jingyuan Tang, Ke Feng, Kai Lin, Xin Lv, Weifeng Chen, Kun Wang, Fei School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China School of Social Sciences Tsinghua University China State Key Laboratory of Software Development Environment Beihang University China Department of Statistics University of Connecticut United States Center for Population Health University of Connecticut Health Center United States Department of Population Health Sciences Weill Cornell Medical College Cornell University United States

Objectives We aim to assess the impact of temperature and relative humidity on the transmission of COVID-19 across communities after accounting for community-level factors such as demographics, socioeconomic status, and human mobility status. Design A retrospective cross-sectional regression analysis via the Fama-MacBeth procedure is adopted. Setting We use the data for COVID-19 daily symptom-onset cases for 100 Chinese cities and COVID-19 daily confirmed cases for 1,005 U.S. counties. Participants A total of 69,498 cases in China and 740,843 cases in the U.S. are used for calculating the effective reproductive numbers. Primary outcome measures Regression analysis of the impact of temperature and relative humidity on the effective reproductive number (R value). Results Statistically significant negative correlations are found between temperature/relative humidity and the effective reproductive number (R value) in both China and the U.S. Conclusions Higher temperature and higher relative humidity potentially suppress the transmission of COVID-19. Specifically, an increase in temperature by 1 degree Celsius is associated with a reduction in the R value of COVID-19 by 0.026 (95% CI [-0.0395,-0.0125]) in China and by 0.020 (95% CI [-0.0311, -0.0096]) in the U.S.;an increase in relative humidity by 1% is associated with a reduction in the R value by 0.0076 (95% CI [-0.0108,-0.0045]) in China and by 0.0080 (95% CI [-0.0150,-0.0010]) in the U.S. Therefore, the potential impact of temperature/relative humidity on the effective reproductive number alone is not strong enough to stop the pandemic. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Incremental Learning: A Closer Look at the Softmax Function

SSRN

引用

SSRN 2024年

作者： Zhai, Zheng Zhang, Jiali Wang, Haiyu Wu, Mingxin Yang, Keshun Qiao, Xiaoyan Sun, Qiang Beijing Normal University No.18 Jinfeng Road Guangdong Zhuhai519087 China Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong China School of Mathematics Sichuan University Chengdu China College of Liberal Arts and Sciences University of Illinois Urbana-Champaign IL United States Department of Statistical Sciences University of Toronto ON Canada Department of Computer Science University of Toronto ON Canada Department of Statistics and Data Science MBZUAI Abu Dhabi United Arab Emirates

This paper investigates the limitations of the widely adopted softmax cross-entropy loss in incremental learning problems. Specifically, we highlight how the shift-invariant property of this loss function can lead to multiple optimal solutions and imbalanced weights across different tasks, which exacerbates catastrophic forgetting. To address these issues, we propose two key modifications to the objective function: (1) regularizing or replacing the original joint distillation loss with a summation of task-specific distillation losses, and/or (2) utilizing a shift-sensitive prediction loss function, such as the binary cross-entropy loss. Numerical experiments validate the effectiveness of these proposals, demonstrating improved prediction accuracy and a significant reduction in forgetting. © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Tensorized Multi-View Kernel Subspace Clustering

引用

ACM Transactions on Intelligent Systems and Technology 1000年

作者： Guang-Yu Zhang Dong Huang Chang-Dong Wang College of Mathematics and Informatics South China Agricultural University China School of Computer Science and Engineering Sun Yat-sen University Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Guangdong Key Laboratory of Big Data Analysis and Processing Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The Anchor-based Multi-view Subspace Clustering (AMSC) has turned into a favourable tool for large-scale multi-view clustering. However, there still exist some limitations to the current AMSC approaches. First, they typically recover anchor graph structure in the original linear space, restricting their feasibility for nonlinear scenarios. Second, they usually overlook the potential benefits of jointly capturing the inter-view and intra-view information for enhancing the anchor representation learning. Third, these approaches mostly perform anchor-based subspace learning by a specific matrix norm, neglecting the latent high-order correlation across different views. To overcome these limitations, this paper presents an efficient and effective approach termed Large-scale Tensorized Multi-view Kernel Subspace Clustering (LTKMSC). Different from the existing AMSC approaches, our LTKMSC approach exploits both inter-view and intra-view awareness for anchor-based representation building. Concretely, the low-rank tensor learning is leveraged to capture the high-order correlation (i.e., the inter-view complementary information) among distinct views, upon which the \(l_{1,2}\) norm is imposed to explore the intra-view anchor graph structure in each view. Moreover, the kernel learning technique is leveraged to explore the nonlinear anchor-sample relationships embedded in multiple views. With the unified objective function formulated, an efficient optimization algorithm that enjoys low computational complexity is further designed. Extensive experiments on a variety of multi-view datasets have confirmed the efficiency and effectiveness of our approach when compared with the other competitive approaches.

关键词： data clustering Multi-view clustering Large-scale clustering Tensorized kernel subspace clustering Inter-view and intra-view awareness

来源：评论

学校读者我要写书评

暂无评论

Category re-balancing based domain adaptive semantic segmentation

引用

Procedia Computer Science 2024年 242卷 1155-1162页

作者： Siyu Zhu Fenfen Zhou Kai Li Minghao Liu Haonan Wen Computer School Beijing information science and technology university 102206 No.55 Taihang Road Changping District Beijing China Beijing Key Laboratory of Information Service Engineering Beijing Union University 100101 Beijing China. College of Robotics Beijing Union University 100027 Beijing China National Engineering Research Center of Visual Technology School of Computer Science Peking University 100871 Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences No.19(A) Yuquan Road Shijingshan District Beijing 100049 P.R. China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences No. 80 of Zhongguancun East Road Haidian District Beijing 100190 Beijing China

The semantic segmentation task faces the bottleneck of high manual annotation costs. Domain adaptive learning provides an effective solution through inter domain knowledge transfer. However, existing domain adaptive semantic segmentation tasks face the situation of category asymmetry between scenes when dealing with complex scenes. Existing methods lack handling of class imbalance in the prediction process. In domain adaptive semantic segmentation tasks, class imbalance limits the performance of inter domain transfer. Our work focuses on the impact of category distribution on domain adaptive semantic segmentation tasks in image pairs. Inspired by long tail learning, we divided categories into head, middle, and tail categories, and designed effective strategies to enhance the contribution of tail categories in domain adaptation tasks. We introduce the concept of category rebalancing into domain adaptive image matching, and our method is lightweight and effective, proving its effectiveness on general datasets.

关键词： Long-tail learning Domain adaptation Semantic segmentation Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Level Image Retrieval in Domain Adaptive Semantic Segmentation

引用

Procedia Computer Science 2024年 242卷 1163-1170页

作者： Siyu Zhu Fenfen Zhou Kai Li Haonan Wen Minghao Liu Computer School Beijing information science and technology university 102206 No.55 Taihang Road Changping District Beijing China Beijing Key Laboratory of Information Service Engineering Beijing Union University 100101 Beijing China. College of Robotics Beijing Union University 100027 Beijing China National Engineering Research Center of Visual Technology School of Computer Science Peking University 100871 Beijing China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences No. 80 of Zhongguancun East Road Haidian District Beijing 100190 Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences No.19(A) Yuquan Road Shijingshan District Beijing 100049 P.R. China

The traditional domain adaptation task is not sufficient in mining inter domain image context. We propose a solution from the perspective of image semantic level retrieval. Image semantic level retrieval is based on the high-level semantics of images, retrieving the similarity or correspondence between images in terms of content and scene between domains. Our work focuses on the meaning, structure, and contextual information expressed by the target image, and retrieves the most relevant image from the source domain to improve the accuracy of domain adaptation. Furthermore, in response to the negative transfer brought about by image retrieval, we will introduce a category level weight adjustment module to further improve the accuracy of semantic level retrieval and weaken the negative impact caused by low precision categories. Finally, we demonstrated the effectiveness of semantic level image retrieval through experiments.

关键词： Image retrieval Domain adaptation Semantic segmentation Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Revealing Interfacial Properties of Inorganic Molecular Crystal Sb2o3 and Monolayer Mos2

SSRN

引用

SSRN 2023年

作者： Liu, Qin Zuo, Yang He, Jingyu Zeng, Minggang Yang, Tong Zhou, Jun Yang, Yulin Song, Ting Ting Wang, Shijie Yang, Ming College of Physics and Space Science China West Normal University Nanchong637002 China Department of Applied Physics The Hong Kong Polytechnic University Hung Hom Hong Kong Institute of High-Performance Computing A∗STAR 1 Fusionopolis Way Singapore138632 Singapore Institute of Materials Research and Engineering A ∗ STAR 2 Fusionopolis Way Singapore138634 Singapore Fujian Provincial Key Laboratory of Optoelectronic Technology and Devices School of Optoelectronic and Communication Engineering Xiamen University of Technology Xiamen361024 China Research Centre on Data Sciences & Artificial Intelligence The Hong Kong Polytechnic University Hung Hom Hong Kong

Inorganic molecule crystal Sb2O3 has been identified as a promising high-k dielectric for direct integration with the two-dimensional semiconductor MoS2. However, a comprehensive understanding of this van der Waals (vdW) interface is still lacking, impeding its applications in high-performance nanoelectronics. In this study, we employ first-principles calculations to elucidate the interfacial interaction and electronic properties of the Sb2O3/monolayer MoS2 interface. We find that a high-performance quasi-vdW interface can be formed between Sb2O3 and monolayer MoS2, as evidenced by weak interfacial interaction, a dangling-bond-free interface, insignificant electron-hole puddle redistribution, and the preserved semiconducting properties of monolayer MoS2. Notably, the interface exhibits a remarkable defect tolerance capability during integration, as Sb2O3 cluster vacancies (the dominant defect in Sb2O3) neither introduce mid-gap states nor significantly affect the interface properties. Besides, our study reveals an asymmetric type-I band alignment at the interface, where the conduction band offset is sufficiently large to minimize electron tunneling. Our work offers a comprehensive understanding of the vdW interface between Sb2O3 and monolayer MoS2, which could potentially advance the development of inorganic molecular crystals as high-k dielectrics for high-performance two-dimensional electronic devices. © 2023, The Authors. All rights reserved.

关键词： Antimony compounds

来源：评论

学校读者我要写书评

暂无评论

Sequential Manipulation Against Rank Aggregation: Theory and Algorithm

arXiv

引用

arXiv 2024年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Liu, Wei Cao, Xiaochun Sun, Yingfei Huang, Qingming The School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China The Tencent Data Platform Shenzhen518054 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-Sen University Shenzhen518107 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China

Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc. Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to manipulate the ranking list. However, the ideal attack opportunity and the excessive adversarial capability cause the existing methods to be impractical. To fully explore the potential risks, we leverage an online attack on the vulnerable data collection process. Since it is independent of rank aggregation and lacks effective protection mechanisms, we disrupt the data collection process by fabricating pairwise comparisons without knowledge of the future data or the true distribution. From the game-theoretic perspective, the confrontation scenario between the online manipulator and the ranker who takes control of the original data source is formulated as a distributionally robust game that deals with the uncertainty of knowledge. Then we demonstrate that the equilibrium in the above game is potentially favorable to the adversary by analyzing the vulnerability of the sampling algorithms such as Bernoulli and reservoir methods. According to the above theoretical analysis, different sequential manipulation policies are proposed under a Bayesian decision framework and a large class of parametric pairwise comparison models. For attackers with complete knowledge, we establish the asymptotic optimality of the proposed policies. To increase the success rate of the sequential manipulation with incomplete knowledge, a distributionally robust estimator, which replaces the maximum likelihood estimation in a saddle point problem, provides a conservative data generation solution. Finally, the corroborating empirical evidence shows that the proposed method manipulates the results of rank aggregation methods in a sequential manner. © 2024, CC BY.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Larger Receptive Field and Context Information for Pose Estimation: Larger Gaussian Kernel

Larger Receptive Field and Context Information for Pose Esti...

引用

High Performance Big data and Intelligent Systems (HPBD&IS)

作者： Junxiao Ma Kai Yang Zunwang Ke Gang Wang Yugui Zhang Fengcai Cao Qi Zhou Yang Fei School of Information Beijing Forestry University Beijing China AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing China CGNPC Uranium Industry Development Co. Ltd. Beijing China School of Software Xinjiang University Urumqi China School of Computing and Data Engineering NingboTech University Ningbo China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China School of Integrated Circuits University of Chinese Academy of Sciences Beijing China Zhongke Shangyi Health Technology (Beijing) Co. Ltd. Beijing China School of Semiconductor Science and Technology South China Normal University GuangZhou China

The field of pose estimation has a wide range of application prospects in various industries in the current era. With the continuous development of deep learning techniques, the effects in the field of human pose estimation are constantly being optimized. However, due to the influence of factors such as occlusion and human posture variability, it is easy to lead to inaccurate identification of keypoints and even keypoints' missing and matching errors, there is still a lot of optimization space for the effect of pose estimation. In this paper, we propose an improvement to generate heatmaps in the training process: increase the radius of the Gaussian kernel and adjust the smoothness of Gaussian distribution to get a larger receptive field, encourage the model to use more context information in prediction, and control other parameters unchanged on the premise of using heatmap regression. Improve keypoint detection performance by optimizing this item. In the experiment, for the COCO-keypoint data set, we selected different methods published in recent years, and after our improvement, we obtained better accuracy and performance than the original method, which proves the validity of our method.

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：