检索结果-南通市图书馆

A new centrality measure based on neighbor loop structure for network dismantling

在线全文

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第2期10卷 472-480页

作者： Qingxia Liu Bang Wang Jiming Qi Xianjun Deng school of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan430074China school of Cyber science and Engineering Huazhong University of Science and TechnologyWuhan430074China

Nearly all real-world networks are complex networks and usually are in danger of ***,it is crucial to exploit and understand the mechanisms of network attacks and provide better protection for network *** dismantling aims to find the smallest set of nodes such that after their removal the network is broken into connected components of sub-extensive *** overcome the limitations and drawbacks of existing network dismantling methods,this paper focuses on network dismantling problem and proposes a neighbor-loop structure based centrality metric,NL,which achieves a balance between computational efficiency and evaluation *** addition,we design a novel method combining NL-based nodes-removing,greedy tree-breaking and ***,we compare five baseline methods with our algorithm on ten widely used real-world networks and three types of model networks including Erd€os-Renyi random networks,Watts-Strogatz smallworld networks and Barabasi-Albert scale-free networks with different network generation *** results demonstrate that our proposed method outperforms most peer methods by obtaining a minimal set of targeted attack ***,the insights gained from this study may be of assistance to future practical research into real-world networks.

关键词： Complex networks Network dismantling Centrality measure

Semantic segmentation via pixel-to-center similarity calculation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao national Key Laboratory of science and technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Meituan Inc. BeijingChina

Since the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel ***,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinction in the same scene could be small,resulting in the limited performance to distinguish different classes in each *** authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class *** weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class ***,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class *** this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class *** CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different *** designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center ***,the CCS layer outputs the processed pixel-to-center similarity as the segmentation *** experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

Highly efficient conversion from classical guided waves to topological chiral edge states

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第2期22卷 221-226页

作者：韩建飞梁锋赵玉林丁霄汪相如赵德双王秉中 school of Physics University of Electronic Science and Technology of ChinaChengdu 611731China school of Optoelectronic science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Electromagnetic topological chiral edge states mimicking the quantum Hall effect have attracted a great deal of attention due to their unique features of free backscattering and immunity against sharp bends and ***,the matching techniques between classical waveguides and the topological one-way waveguide deserve more attention for real-world *** this paper,a highly efficient conversion structure between a classical rectangular waveguide and a topological one-way waveguide is proposed and demonstrated at the microwave frequency,which efficiently converts classical guided waves to topological one-way edge states.A tapered transition is designed to match both the momentum and impedance of the classical guided waves and the topological one-way edge *** the conversion structure,the waves generated by a point excitation source can be coupled to the topological one-way waveguide with very high coupling efficiency,which can ensure high transmission of the whole system(i.e.,from the source and the receiver).Simulation and measurement results demonstrate the proposed *** investigation is beneficial to the applications of topological one-way waveguides and opens up a new avenue for advanced topological and classical integrated functional devices and systems.

关键词： guided waves highly efficient conversion photonic crystals topological chiral edge states

Feature-Grounded Single-Stage Text-to-Image Generation

在线全文

学校读者我要写书评

暂无评论

Tsinghua science and technology 2024年第2期29卷 469-480页

作者： Yuan Zhou Peng Wang Lei Xiang Haofeng Zhang school of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing 210044China school of Computer science and Engineering Nanjing University of Science and TechnologyNanjing 210094China

Recently,Generative Adversarial Networks(GANs)have become the mainstream text-to-image(T2I)***,a standard normal distribution noise of inputs cannot provide sufficient information to synthesize an image that approaches the ground-truth image ***,the multistage generation strategy results in complex T2I ***,this study proposes a novel feature-grounded single-stage T2I model,which considers the“real”distribution learned from training images as one input and introduces a worst-case-optimized similarity measure into the loss function to enhance the model's generation *** results on two benchmark datasets demonstrate the competitive performance of the proposed model in terms of the Frechet inception distance and inception score compared to those of some classical and state-of-the-art models,showing the improved similarities among the generated image,text,and ground truth.

关键词： text-to-image(T2I) feature-grounded single-stage generation Generative Adversarial Network(GAN)

Task-specific Part Discovery for Fine-grained Few-shot Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第5期21卷 954-965页

作者： Yongxian Wei Xiu-Shen Wei school of Computer science and technology Nanjing University of Science and TechnologyNanjing210094China

Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot *** work always relies on the learned object parts in a unified manner,where they attend the same object parts(even with common attention weights)for different few-shot episodic *** this paper,we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task,since the parts that can distinguish different tasks are naturally *** for a few-shot task,after obtaining part-level deep features,we learn a task-specific part-based dictionary for both aligning and reweighting part features in an ***,part-level categorical prototypes are generated based on the part features of support data,which are later employed by calculating distances to classify query data for *** retain the discriminative ability of the part-level representations(i.e.,part features and part prototypes),we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final *** experiments on five fine-grained benchmarks show the superiority of our method,especially for the 1-shot setting,gaining 0.12%,8.56%and 5.87%improvements over state-of-the-art methods on CUB,Stanford Dogs,and Stanford Cars,respectively.

关键词： Fine-grained image recognition few-shot learning transductive learning visual dictionary part feature discovery

A Constraint Adaptive Multi-Tasking Differential Evolution Algorithm:Designed for Dispatch of Integrated Energy System in Coal Mine

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua science and technology 2024年第2期29卷 368-385页

作者： Canyun Dai Xiaoyan Sun Hejuan Hu Yong Zhang Dunwei Gong school of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China school of Information science and technology Qingdao University of Science and TechnologyQingdao 266061China

The dispatch of integrated energy systems in coal mines(IES-CM)with mine-associated supplies is vital for efficient energy utilization and carbon emissions ***,IES-CM dispatch is highly challenging due to its feature as multi-objective and strong *** constrained multi-objective evolutionary algorithms often fall into locally feasible domains with poorly distributed Pareto front,which greatly deteriorates dispatch *** tackle this problem,we transform the traditional dispatch model of IES-CM into two tasks:the main task with all constraints and the helper task with constraint *** we propose a constraint adaptive multi-tasking differential evolution algorithm(CA-MTDE)to optimize these two tasks *** helper task with constraint adaptive is developed to obtain infeasible solutions near the feasible *** purpose of this infeasible solution is to transfer guiding knowledge to help the main task move away from local ***,a dynamic dual-learning strategy using DE/current-to-rand/1 and DE/current-to-best/1 is developed to maintain task diversity and ***,we comprehensively evaluate the performance of CA-MTDE by applying it to a coal mine in Shanxi Province,considering two IES-CM *** demonstrate the feasibility of CA-MTDE and its ability to generate a Pareto front with exceptional convergence,diversity,and distribution.

关键词： dispatch integrated energy system coal mine evolutionary multi-tasking constraint differential evolution

Metarelation2vec:A Metapath-Free Scalable Representation Learning Model for Heterogeneous Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua science and technology 2024年第2期29卷 553-575页

作者： Lei Chen Yuan Li Yong Lei Xingye Deng school of Information and Electrical Engineering Hunan University of Science and TechnologyXiangtan 411201China school of Computer science and Engineering Hunan University of Science and TechnologyXiangtan 411201China

Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning ***,any metapaths consisting of multiple,simple metarelations must be driven by domain *** sensitive,expensive,and limited metapaths severely reduce the flexibility and scalability of the existing models.A metapath-free,scalable representation learning model,called Metarelation2vec,is proposed for HNs with biased joint learning of all metarelations in a bid to address this ***,a metarelation-aware,biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given ***,grouped nodes by the type,a common and shallow skip-gram model is used to separately learn structural proximity for each node ***,grouped links by the type,a novel and shallow model is used to separately learn the semantic proximity for each link ***,supervised by the cooperation probabilities of all meta-words,the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs,ensuring the accuracy and scalability of the *** experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.

关键词： metarelation random walk heterogeneous network metapath representation learning

Unsupervised Multi-Expert Learning Model for Underwater Image Enhancement

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 708-722页

作者： Hongmin Liu Qi Zhang Yufan Hu Hui Zeng Bin Fan the school of Intelligence science and technology and the Institute of Artificial Intelligence University of Science and Technology BeijingBeijing 100083China the school of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China IEEE

Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded *** methods feed the whole image directly into the model for ***,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the *** address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color ***,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater *** on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater ***,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,*** addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced *** experiments on public datasets demonstrate that our method achieves more pleasing results in vision *** metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.

关键词： Multi-expert learning underwater image enhancement unsupervised learning

Graphene oxide/Al_(2)O_(3)-based diffusive memristor cells:enabling robust crossbar arrays for multidisciplinary applications

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2024年第8期43卷 3997-4005页

作者： Chen Liu Jun-Cheng Jin Yi-Ke Xiao Xin-Xin Wang Ping-Yuan Yan Yan-Qiang Cao Li-Yong Jiang Chuan-Xiang Sheng Ye-Feng Yu school of Microelectronics Nanjing University of Science and TechnologyNanjing 210094China school of science Nanjing University of Science and TechnologyNanjing210094China school of Information science and technology Fudan UniversityShanghai 200433China

A memristor crossbar array (MCA) has emerged as a cutting-edge platform for advanced memory and neuromorphic computing hardware,offering unrivaled bit-level storage density.A diffusive memristor cell (DMC) is particularly well-suited for MCA integration due to its inherent threshold switching characteristics as a selector,effectively addressing current sneak path *** DMC's potential is acknowledged,it necessitates furtherexploration of their practical applicability.

关键词： crossbar arrays offering