检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design issues in ZigBee-based sensor network for healthcare applications

Design issues in ZigBee-based sensor network for healthcare ...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Jin Soo Choi Meng Chu Zhou Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China ECE Department New Jersey Institute of Technology Newark NJ USA

IEEE 802.15.4/ZigBee sensor networks support small power consumption and node expansion compared to other network standards for WSN. Body sensor networks (BSN) require a number of sensors for sensing medical information from human body, and low power consumption to monitor a patient's status for a long time. However, ZigBee has limited bandwidth and is thus hard to support real time data transmission because of the adoption of CSMA-CA as its medium access control (MAC) protocol. In this paper, we will analyze the reasonable number of nodes, size of payload and packet interval for best QoS for such network. It is found that an appropriate MAC parameters setting can improve the QoS compared to the default setting in IEEE 802.15.4 specification. The effective data rate, average end-to-end delay and packet delivery ratio are found via simulation for various network settings. The results are useful for the construction of ZigBee networks for patient monitoring and care.

关键词： Delay IEEE 802.15 Standards Zigbee Monitoring Payloads Medical services Data models

来源：评论

学校读者我要写书评

暂无评论

HPC AI500: A Benchmark Suite for HPC AI systems 1st

HPC AI500: A Benchmark Suite for HPC AI Systems

引用

1st International Symposium on Benchmarking, Measuring, and Optimization, Bench 2018

作者： Jiang, Zihan Gao, Wanling Wang, Lei Xiong, Xingwang Zhang, Yuchen Wen, Xu Luo, Chunjie Ye, Hainan Lu, Xiaoyi Zhang, Yunquan Feng, Shengzhong Li, Kenli Xu, Weijia Zhan, Jianfeng State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Dover DE United States Beijing Academy of Frontier Sciences and Technology Beijing China State University of New York Buffalo United States Department of Computer Science and Engineering The Ohio State University Columbus United States National Supercomputing Center in Shenzhen Shenzhen China National Supercomputing Center in Changsha Changsha China National Supercomputing Center in Jinan Jinan China Texas Advanced Computing Center The Texas University at Austin Austin United States

ISBN: (纸本)9783030328122

In recent years, with the trend of applying deep learning (DL) in high performance scientific computing, the unique characteristics of emerging DL workloads in HPC raise great challenges in designing, implementing HPC AI systems. The community needs a new yard stick for evaluating the future HPC systems. In this paper, we propose HPC AI500—a benchmark suite for evaluating HPC systems that running scientific DL workloads. Covering the most representative scientific fields, each workload from HPC AI500 is based on real-world scientific DL applications. Currently, we choose 14 scientific DL benchmarks from perspectives of application scenarios, data sets, and software stack. We propose a set of metrics for comprehensively evaluating the HPC AI systems, considering both accuracy, performance as well as power and cost. We provide a scalable reference implementation of HPC AI500. The specification and source code are publicly available from http://***/HPCAI500/***. Meanwhile, the AI benchmark suites for datacenter, IoT, Edge are also released on the BenchCouncil web site. © 2019, Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Survey: Hardware Trojan Detection for Netlist

Survey: Hardware Trojan Detection for Netlist

引用

Asian Test Symposium (ATS)

作者： Yipei Yang Jing Ye Yuan Cao Jiliang Zhang Xiaowei Li Huawei Li Yu Hu State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Hohai University Nanjing China Hunan University Changsha China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728174679

ISBN: (纸本)9781728174686

The development of integrated circuit technology is accompanied by potential threats. Malicious modifications to circuits, known as hardware Trojans, are major security concerns. This paper gives a survey of hardware Trojan detection methods towards gate-level netlists. The detection methods are divided into search-based, threshold-based, and machine learning-based ones. This paper compares and analyzes existing works from aspects of feature selection, data balancing techniques, classification criterion, detection range. The experimental results are also selected for comparison.

关键词： Trojan horses Hardware Logic gates Feature extraction Security Integrated circuit modeling Flip-flops

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

Improving the performance of stochastic local search for maximum vertex weight clique problem using programming by optimization

arXiv

引用

arXiv 2020年

作者： Chu, Yi Luo, Chuan Hoos, Holger H. Lin, Qingwei You, Haihang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Microsoft Research China Leiden Institute of Advanced Computer Science Leiden University Leiden Netherlands

The maximum vertex weight clique problem (MVWCP) is an important generalization of the maximum clique problem (MCP) that has a wide range of real-world applications. In situations where rigorous guarantees regarding the optimality of solutions are not required, MVWCP is usually solved using stochastic local search (SLS) algorithms, which also define the state of the art for solving this problem. However, there is no single SLS algorithm which gives the best performance across all classes of MVWCP instances, and it is challenging to effectively identify the most suitable algorithm for each class of MVWCP instances. In this work, we follow the paradigm of Programming by Optimization (PbO) to develop a new, flexible and highly parametric SLS framework for solving MVWCP, combining, for the first time, a broad range of effective heuristic mechanisms. By automatically configuring this PbO-MWC framework, we achieve substantial advances in the state-of-the-art in solving MVWCP over a broad range of prominent benchmarks, including two derived from real-world applications in transplantation medicine (kidney exchange) and assessment of research excellence. Copyright © 2020, The Authors. All rights reserved.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Interacting Diseases

引用

Physical Review X 2014年第4期4卷 041005-041005页

作者： Joaquín Sanz Cheng-Yi Xia Sandro Meloni Yamir Moreno Institute for Biocomputation and Physics of Complex Systems (BIFI) University of Zaragoza Zaragoza 50018 Spain Department of Theoretical Physics University of Zaragoza Zaragoza 50009 Spain Key Laboratory of Computer Vision and System (Ministry of Education) and Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin 300191 People’s Republic of China Complex Networks and Systems Lagrange Lab Institute for Scientific Interchange Turin 10126 Italy

Current modeling of infectious diseases allows for the study of complex and realistic scenarios that go from the population to the individual level of description. However, most epidemic models assume that the spreading process takes place on a single level (be it a single population, a metapopulation system, or a network of contacts). In particular, interdependent contagion phenomena can be addressed only if we go beyond the scheme-one pathogen-one network. In this paper, we propose a framework that allows us to describe the spreading dynamics of two concurrent diseases. Specifically, we characterize analytically the epidemic thresholds of the two diseases for different scenarios and compute the temporal evolution characterizing the unfolding dynamics. Results show that there are regions of the parameter space in which the onset of a disease’s outbreak is conditioned to the prevalence levels of the other disease. Moreover, we show, for the susceptible-infected-susceptible scheme, that under certain circumstances, finite and not vanishing epidemic thresholds are found even at the limit for scale-free networks. For the susceptible-infected-removed scenario, the phenomenology is richer and additional interdependencies show up. We also find that the secondary thresholds for the susceptible-infected-susceptible and susceptible-infected-removed models are different, which results directly from the interaction between both diseases. Our work thus solves an important problem and paves the way toward a more comprehensive description of the dynamics of interacting diseases.

关键词： Complex systems Interdisciplinary physics Statistical physics

来源：评论

学校读者我要写书评

暂无评论

Prediction of Register Instance Usage and Time-sharing Register for Extended Register Reuse Scheme

Prediction of Register Instance Usage and Time-sharing Regis...

引用

Asia and South Pacific Design Automation Conference

作者： Shuxin Zhou Huandong Wang Dong Tong State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Loongson Corporation Beijing China Peking University Beijing China

ISBN: (数字)9781450379991

ISBN: (纸本)9781728180571

Register renaming is the key for the performance of out-of-order processors. However, the release mechanism of the physical register may cause a waste from time dimension. The register reuse technique is the earliest solution to release a physical register at renaming stage, which takes the advantage of those register instances with only one time use. However, the range of possible reuse mined by this scheme is not high, and the physical structure of the register have to be modified. Aiming at these two problems, we propose an extended register reuse scheme. Our work presents: 1) prediction of the use times of the register instance, so as to reuse the physical registers at the end of the last use, to expand the range of possible reuse. 2) A design of time-sharing register file with little overheads which is implemented by Backup Registers, avoiding to modify the physical register structure. Compared with the original register reuse technique, this work achieves 8.5% performance improvement, alternatively, 9.6% decrease of the number of physical registers with minor hardware overhead.

关键词： Out of order Program processors Design automation Asia Hardware Registers

来源：评论

学校读者我要写书评

暂无评论

Instruction level test for parallel multipliers

Instruction level test for parallel multipliers

引用

IEEE International Conference on Electronics, Circuits and systems (ICECS)

作者： Ma Lin Gao Yan Chinese Academy of Sciences Beijing China Key Laboratory of Computer System and Architecturen+î Institute of Computing Technology Chinese Academy and Sciences Beijing China College of Electronics and Information Engineering University of Tongji Shanghai China

Multiplication operations are the normal operations in operating systems or scientific calculations. Multipliers embedded in processors, DSP or SoC are well optimized for best performance, and they are sensitive to test overhead. Instruction level test is a popular functional test approach for microprocessors test, and it can get satisfactory test results. But for the multipliers, one important part of microprocessors, there is no detail on how to testing them. This paper presents an instruction level test approach for the multiplier test. The proposed approach does not modify the multipliers and does not need any extra logic just using instructions of the processors to test processorspsila multipliers. Sequentially it does not have any test cost on area or timing. Moreover the instruction-level test is suited for at-speed test in nature. Experimental results on the real processorpsilas circuits show that the instruction level test approach has good effect on parallel multipliers.

关键词： Circuit testing Built-in self-test system testing Circuit faults Sequential analysis Microprocessors Automatic testing Costs Very large scale integration Integrated circuit testing

来源：评论

学校读者我要写书评

暂无评论

Transmission mode selection for downlink transmission in LTE-A networks

Transmission mode selection for downlink transmission in LTE...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Jian Yu Geoffrey Ye Li Changchuan Yin Xiaolong Zhu Yusun Fu Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta Georgia USA Huawei Shanghai Research Institute Shanghai China

In this paper, we investigate mode selection for coordinated multi-point (CoMP) transmission in downlink LTE-A networks, where inter-cluster interference exists. The proposed scheme selects the single-cell (SC) or coordinated beamforming (CB) transmission mode according to interference level to maximize the weighted sum rate with fairness consideration. To formulate the optimization problem, an approximated closed-form expression for the achievable rate is derived by modeling the probability distributions of signal and interference powers as Gamma distributions. Since the original optimization problem is a combinatorial and non-convex one with high complexity, a low-complexity and sub-optimal algorithm is proposed, which first performs coordinated cell selection and then transmission mode selection. Simulation results show that the closed-form approximation of the achievable rate is very tight and the proposed mode selection scheme can improve the average system throughput by 13% and the 10th percentile user throughput by 10% compared with the existing scheme.

关键词： Interference Optimization Approximation methods Closed-form solutions Downlink Signal to noise ratio Land mobile radio

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：