检索结果-内蒙古大学图书馆

A Self-adaptive PSO-Based Dynamic Scheduling Method on Hierarchical Cloud Computing 1

9th EAI International Conference on Cloud Computing, CloudComp 2019 and the 4th EAI International Conference on Smart Grid and Innovative Frontiers in Telecommunications, SmartGIFT 2019

作者： Meng, Shunmei Huang, Weijia Xu, Xiaolong Li, Qianmu Dou, Wanchun Liu, Bowen Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9783030485139

ISBN: (纸本)9783030485122

Edge computing has been envisioned as an emerging and prospective computing paradigm for its advantage of low latency, which uses local resources. However, the edge resources are usually limited and could not meet end-users’ diversified requirement. Cloud computing paradigm could provide scalable and centralized resources with high computational capabilities, but it has latency issues. Thus it is suggested to combine both computing paradigms together to improve the performance of mobile applications. In this paper, we propose a self-adaptive dynamic scheduling approach based on hierarchical heterogeneous clouds. Our scheduling mechanism considers not only schedule planning but also dynamic scheduling on heterogeneous clouds. Firstly, a self-adaptive scheduling mechanism based on a meta-heuristic optimization algorithm, PSO (Particle Swarm Optimization), is presented for schedule planning. Then a dynamic scheduling mechanism on dynamic partial workflow model is proposed for dynamic optimization during the execution. Finally, external experiments compared with other methods are conducted to demonstrate the effectiveness of our proposal. © 2020, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Channel-Wise and Spatial Feature Recalibration Network for Nuclear Cataract Classification

Channel-Wise and Spatial Feature Recalibration Network for N...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Zhang, Xiaoqing Xu, Gelei Shen, Junyong Xiao, Zunjie Yan, Qiuyang Yuan, Jin Higashita, Risa Liu, Jiang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China Sun Yat-sen University State Key Laboratory of Ophthalmology Guangzhou China Tomey Corporation Japan Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Nuclear cataract (NC) is a prior age-related disease for blindness and vision impairment globally. Anterior segment optical coherence tomography (AS-OCT) image is a new ophthalmology image, which can capture the lens nucleus region clearly compared with other ophthalmic images, e.g., slit lamp images. Clinical research has suggested that features e.g., mean from AS-OCT images have varying correlations with NC severity levels. However, existing convolutional neural network (CNN) based NC classification works have not incorporated the clinical features into the network design to improve the performance. To this end, we propose a novel channel-wise and spatial feature recalibration network (CSFR-Net) to predict NC severity levels automatically, which is built on a stack of channel-wise and spatial feature recalibration (CSFR) modules. In each CSFR module, we construct a channel-wise feature recalibration block and a spatial feature recalibration block to recalibrate intermediate feature maps dynamically. This feature recalibration strategy enables CSFR-Net to highlight feature representations and suppress unnecessary ones in a global-and-local manner. We conduct extensive experiments on a clinical AS-OCT image dataset and CIFAR benchmarks. The results show that our CSFR-Net achieves better performance than state-of-the-art methods with less model complexity. © 2022 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Effective Entry-Wise Flow for Molecule Generation

Effective Entry-Wise Flow for Molecule Generation

引用

International Conference on Data Engineering

作者： Qifan Zhang Junjie Yao Yuquan Yang Yizhou Shi Wei Gao Xiaoling Wang School of Computer Science and Technology East China Normal University Software Engineering Institute East China Normal University Shanghai Key Laboratory of Trustworthy Computing Department of Chemistry University of Massachusetts Boston University of Michigan Ann Arbor.

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Molecule generation is a critical process in the fields of drug discovery and materials science. Recently, generative models based on normalizing flows have demonstrated significant potential in this domain. These models are particularly suited for handling the symmetrical and complex chemical structures often encountered in molecular datasets. Despite their promising nature, normalizing flow-based models for molecule generation face considerable challenges. The complexity of molecule representation, the rigorous demands of optimization, and the scarcity of training labels in molecular datasets contribute to these difficulties. Additionally, adequately and comprehensively learning the distribution of molecular datasets remains a formidable task. In this paper, we delve into the intricate entry-wise modules in vanilla flows, introducing an effective variation of flow-based models. Our proposed approach innovatively encapsulates affine coupling transformations within normalizing flows. Furthermore, we deconstruct existing invertible flow models, integrating them with newly developed entry-wise transformations. Our experimental studies demonstrate that these proposed entry-wise modules, when incorporated into standard flow-based models, surpass other generative models in performance on various representative datasets and generation tasks. Notably, in the context of low-resourced molecular graph generation, our model achieves remarkable performance compared to its counterparts.

关键词： Training Couplings Materials science and technology Interpolation Data engineering Drug discovery Task analysis

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS

arXiv

引用

arXiv 2023年

作者： Wang, Li Zhang, Xinyu Zhao, Fachuan Wu, Chuze Wang, Yichen Song, Ziying Yang, Lei Li, Jun Liu, Huaping Harbin150001 China The State Key Laboratory of Automotive Safety and Energy The School of Vehicle and Mobility Tsinghua University Beijing100084 China The School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China The State Key Laboratory of Intelligent Technology and the Systems Department of Computer Science and Technology Tsinghua University Beijing100084 China

Non-maximum suppression (NMS) is an essential post-processing module used in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficulties in determining appropriate thresholds can affect the resulting accuracy directly. To address these issues, we introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering. The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process. Adequate validation experiments are conducted using the mainstream KITTI and large-scale Waymo 3D object detection benchmarks. The results of these tests demonstrate the proposed Fuzzy-NMS module can improve the accuracy of numerous recently NMS-based detectors significantly, including PointPillars, PV-RCNN, and IA-SSD, etc. This effect is particularly evident for small objects such as pedestrians and bicycles. As a plug- and-play module, Fuzzy-NMS does not need to be retrained and produces no obvious increases in inference time. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Generalized Cross-Entropy Benchmarking for Random Circuits with Ergodicity

arXiv

引用

arXiv 2025年

作者： Cheng, Bin Meng, Fei Zhang, Zhi-Jiong Yung, Man-Hong Shenzhen Institute for Quantum Science and Engineering Department of Physics Southern University of Science and Technology Shenzhen518055 China Centre for Quantum Technologies National University of Singapore Singapore Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Department of Physics City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong QICI Quantum Information and Computation Initiative Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong International Quantum Academy Shenzhen518048 China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Cross-entropy benchmarking is a central technique used to certify a quantum chip in recent experiments. To better understand its mathematical foundation and develop new benchmarking schemes, we introduce the concept of ergodicity to random circuit sampling and find that the Haar random quantum circuit satisfies an ergodicity condition—the average of certain types of post-processing function over the output bit strings is close to the average over the unitary ensemble. For noiseless random circuits, we prove that the ergodicity holds for polynomials of degree t with positive coefficients and when the random circuits form a unitary 2t-design. For strong enough noise, the ergodicity condition is violated. This suggests that ergodicity is a property that can be exploited to certify a quantum chip. We formulate the deviation of ergodicity as a measure for quantum chip benchmarking and show that it can be used to estimate the circuit fidelity for global depolarizing noise and weakly correlated noise. For a quadratic post-processing function, our framework recovers Google’s result on estimating the circuit fidelity via linear cross-entropy benchmarking (XEB), and we give a sufficient condition on the noise model characterizing when such estimation is valid. Our results establish an interesting connection between ergodicity and noise in random circuits and provide new insights into designing quantum benchmarking schemes. Copyright © 2025, The Authors. All rights reserved.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

M-Detr: Multi-Scale Detr for Optical Music Recognition

SSRN

引用

SSRN 2023年

作者： Luo, Fei Dai, Yifan Fuentes, Joel Ding, Weichao Zhang, Xueqin East China University of Science and Technology Shanghai China Department of Computer Science and Information Technologies Universidad del Bío-Bío Chillán3780000 Chile Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

As a new paradigm for object detection, DETR (detection transformer) has the ability to associate contextual information, which is very suitable for optical music recognition (OMR). This paper proposes a novel multi-scale detection transformer (M-DETR) for OMR with a multi-scale feature fusion mechanism and improved attention mechanisms. First, the feature fusion mechanism is combined with backbone networks to let the M-DETR network get richer multi-scale information. Then, a key-region attention mechanism is incorporated based on the character that the key information in a score image. Finally, the pre-context attention mechanism enables the network to make better use of the contextual association between recognition targets in music scores. Experiment results show that M-DETR achieves recognition accuracy of 90.6% for 7 typical small-sized notes, which is better than Faster R-CNN and YOLO v5, and the improvement rate is 10.02% compared to the original DETR algorithm. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Improving Variational Autoencoders with Density Gap-based Regularization

arXiv

引用

arXiv 2022年

作者： Zhang, Jianfei Bai, Jun Lin, Chenghua Wang, Yanmeng Rong, Wenge State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

Variational autoencoders (VAEs) are one of the most powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converging to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and the hole problem, i.e., the mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization, and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and posterior collapse. Copyright © 2022, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

isQ: Towards a Practical software Stack for Quantum Programming

arXiv

引用

arXiv 2022年

作者： Guo, Jingzhe Lou, Huazhe Li, Riling Fang, Wang Liu, Junyi Long, Peixun Ying, Shenggang Ying, Mingsheng Department of Computer Science and Technology Tsinghua University Beijing China Arclight Quantum Computing Inc Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

We introduce isQ, a new software stack for quantum programming in an imperative programming language, also named isQ. The aim of isQ is to make the programmers write quantum programs as conveniently as possible. In particular: 1) The isQ language and its compiler contain many features, including some not well supported by (most) other quantum programming platforms, e.g. classical control flow such as recursion;decomposition of self-defined unitary gates;and oracle programming and its circuit realization. 2) To make it flexible, an isQ program can be compiled into several kinds of intermediate representation, including OpenQASM 3.0, QIR and QCIS (specially tailored for the superconducting quantum hardware at USTC). 3) Besides interfacing isQ with true superconducting hardware, a QIR simulator is also developed for demonstration and testing of isQ programs. © 2022, CC BY.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Video Object Segmentation with Comprehensive Scene Awareness

SSRN

引用

SSRN 2022年

作者： Ji, Chuanjun Chen, Yadang Yang, Zhi-Xin Wu, Enhua The State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China The State Key Laboratory of Computer Science Institute of Software University of Chinese Academy of Sciences Beijing100190 China

This paper aims to investigate the video object segmentation task (VOS) in semi-supervised settings, which estimates the mask of the target object in subsequent frames based on its mask in the initial frame. Currently, the most advanced methods primarily depend on generative target appearance models, but as they are susceptible to background distractors resembling the target objects, only limited robustness can be achieved. To eliminate this influence, a semi-supervised VOS method with comprehensive scene awareness is proposed in this study, which consists of a target appearance network and a scenario knowledge network. The target appearance network adopts a memory-based architecture to obtain the appearance cues of target objects. The scenario knowledge network captures detailed environmental cues, such as the position of distractor objects, which greatly assists in locating the target. To ensure that the scenario knowledge is learned accurately and effectively combined with the output of the target appearance network, a union loss function is designed to supervise the network model for training. On several prevalent benchmarks, this method achieves a favorable performance compared to the most advanced methods currently available. The scenario knowledge network contains complementary information and provides a considerable performance increase, even when considering a strong appearance model. © 2022, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Improving variational autoencoders with density gap-based regularization 22

Improving variational autoencoders with density gap-based re...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jianfei Zhang Jun Bai Chenghua Lin Yanmeng Wang Wenge Rong State Key Laboratory of Software Development Environment Beihang University China and School of Computer Science and Engineering Beihang University China Department of Computer Science University of Sheffield United Kingdom Ping An Technology China

ISBN: (纸本)9781713871088

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：