检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, 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

Manifold Constraint Regularization for Remote Sensing Image Generation

arXiv

引用

arXiv 2023年

作者： Su, Xingzhe Zheng, Changwen Qiang, Wenwen Wu, Fengge Zhao, Junsuo Sun, Fuchun Xiong, Hui The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China The National Key Laboratory of Space Integrated Information System Department of Computer Science and Technology Tsinghua University Beijing China The Hong Kong University of Science and Technology China

Generative Adversarial Networks (GANs) have shown notable accomplishments in remote sensing domain. However, this paper reveals that their performance on remote sensing images falls short when compared to their impressive results with natural images. This study identifies a previously overlooked issue: GANs exhibit a heightened susceptibility to overfitting on remote sensing images. To address this challenge, this paper analyzes the characteristics of remote sensing images and proposes manifold constraint regularization, a novel approach that tackles overfitting of GANs on remote sensing images for the first time. Our method includes a new measure for evaluating the structure of the data manifold. Leveraging this measure, we propose the manifold constraint regularization term, which not only alleviates the overfitting problem, but also promotes alignment between the generated and real data manifolds, leading to enhanced quality in the generated images. The effectiveness and versatility of this method have been corroborated through extensive validation on various RS datasets and GAN models. The proposed method not only enhances the quality of the generated images, reflected in a 3.13% improvement in Frechet Inception Distance (FID) score, but also boosts the performance of the GANs on downstream tasks, evidenced by a 3.76% increase in classification accuracy. The source code is available at https://***/rootSue/Manifold-RSGAN. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

VDFSR Knowledge based Variable-Density Photographic Film to Sound Generation Method

VDFSR Knowledge based Variable-Density Photographic Film to ...

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Wang, Ruiqi Jin, Cong Yu, Yinan Zhai, Yutong National Key Laboratory of Scattering and Radiation Beijing China University of China School of Data Science and Intelligent Media Communication Beijing China China Norinco Company School of Aerospace Engineering Beijing Institute of Technology Armament Research and Development Institute Beijng China Casic Space Engineering Development Co. Ltd. Beijing China

ISBN: (纸本)9798350376739

Image domain film to sound generation (IDFSG) is a research hotspot in film industry and cross-modal learning. Existing researches neglect sound generation need for variable density film soundtrack. To solve the problem of constructing sound generation processes during variable density film soundtrack reproduction (VDFSR), we propose a PF2SG method based on the VDFSR knowledge, which can effectively achieve high-quality sound generation performance. Specifically, from the perspective of mining the intrinsic consistency of different types of signal capability transformations, we embed variable density film soundtrack reproduction knowledge into the corresponding sound generation process in stages. Moreover, to further enhance the stability of our IDFSG method, we design a sound reproduction module for variable density film soundtrack that integrates the photometric sampling interval based on the mechanical structure of the film projector. Our method effectively explores the intrinsic consistency between the image domain information and the audio domain information during VD film sound generation. Experiments have shown that our method can effectively generate higher quality audio compared to existing methods and commercial devices. © 2024 IEEE.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

A Topic-Aware Graph-Based Neural Network for User Interest Summarization and Item Recommendation in Social Media 28th

A Topic-Aware Graph-Based Neural Network for User Interest ...

引用

28th International Conference on database systems for Advanced Applications, DASFAA 2023

作者： Chen, Junyang Fan, Ge Gong, Zhiguo Li, Xueliang Leung, Victor C. M. Wang, Mengzhu Yang, Ming College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen China Tencent Inc. Shenzhen China State Key Laboratory of Internet of Things for Smart City Department of Computer Information Science University of Macau China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)9783031306716

User-generated content is daily produced in social media, as such user interest summarization is critical to distill salient information from massive information. While the interested messages (e.g., tags or posts) from a single user are usually sparse becoming a bottleneck for existing methods, we propose a topic-aware graph-based neural interest summarization method (UGraphNet), enhancing user semantic mining by unearthing potential user relations and jointly learning the latent topic representations of posts that facilitates user interest learning. Experiments on two datasets collected from well-known social media platforms demonstrate the superior performance of our model in the tasks of user interest summarization and item recommendation. Further discussions also show that exploiting the latent topic representations and user relations are conductive to the user automatic language understanding. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust Optimization for Computation Offloading in Aerial Access Networks

Distributionally Robust Optimization for Computation Offload...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Jiang, Guanwang Jia, Ziye He, Lijun Dong, Chao Wu, Qihui Han, Zhu Nanjing University of Aeronautics and Astronautics Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing211106 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China Northwestern Polytechnical University School of Software Xi'an710072 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States

ISBN: (纸本)9798350351255

With the rapid increment of multiple users for data offloading and computation, it is challenging to guarantee the quality of service (QoS) in remote areas. To deal with the challenge, it is promising to combine aerial access networks (AANs) with multi-access edge computing (MEC) equipments to provide computation services with high QoS. However, as for uncertain data sizes of tasks, it is intractable to optimize the offloading decisions and the aerial resources. Hence, in this paper, we consider the AAN to provide MEC services for uncertain tasks. Specifically, we construct the uncertainty sets based on historical data to characterize the possible probability distribution of the uncertain tasks. Then, based on the constructed uncertainty sets, we formulate a distributionally robust optimization problem to minimize the system delay. Next, we relax the problem and reformulate it into a linear programming problem. Accordingly, we design a MEC-based distributionally robust latency optimization algorithm. Finally, simulation results reveal that the proposed algorithm achieves a superior balance between reducing system latency and minimizing energy consumption, as compared to other benchmark mechanisms in the existing literature. © 2024 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Improving Code Search with Multi-Modal Momentum Contrastive Learning

Improving Code Search with Multi-Modal Momentum Contrastive ...

引用

IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Zejian Shi Yun Xiong Yao Zhang Zhijie Jiang Jinjing Zhao Lei Wang Shanshan Li Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Peng Cheng Laboratory Shenzhen China School of Computer National University of Defense Technology China National Key Laboratory of Science and Technology on Information System Security China

Contrastive learning has recently been applied to enhancing the BERT-based pre-trained models for code search. However, the existing end-to-end training mechanism cannot sufficiently utilize the pre-trained models due to the limitations on the number and variety of negative samples. In this paper, we propose MoCoCS, a multi-modal momentum contrastive learning method for code search, to improve the representations of query and code by constructing large-scale multi-modal negative samples. MoCoCS increases the number and the variety of negative samples through two optimizations: integrating multi-batch negative samples and constructing multi-modal negative samples. We first build momentum contrasts for query and code, which enables the construction of large-scale negative samples out of a mini-batch. Then, to incorporate multi-modal code information, we build multi-modal momentum contrasts by encoding the abstract syntax tree and the data flow graph with a momentum encoder. Experiments on CodeSearchNet with six programming languages demonstrate that our method can further improve the effectiveness of pre-trained models for code search.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The design and investigation of hydrogel-based metamaterials with ultra large negative hygroscopic expansion ratio

引用

International Journal of Smart and Nano Materials 2022年第1期13卷 114-129,I0007页

作者： Lian-Hua Ma Su-Dong Wang Jia Liu Hong Gao Wei Zhou Non-destructive Testing Laboratory School of Quality and Technical SupervisionHebei UniversityBaodingHebei071002China National&local Joint Engineering Research Center of Metrology Instrument and System Hebei UniversityBaodingHebei071002China Hebei Key Laboratory of Energy Metering and Safety Testing Technology Hebei UniversityBaodingHebei071002China Material Reliability Center China academy of space technologyBeijing100029China

A design strategy for a mechanical metamaterial with large negative hygroscopic expansion(NHE)was proposed in this *** from the reported structures,the present metamaterial is designed by constructing repeated lattice microstructure consisting of curved ligaments incorporating hydrogel active layers and polymer support layers and straight polymer *** immersed in the solution environment,the swelling of hydrogel layer of such composite structure induces the reversed bending of the ligament,leading to the overall ultra-large shrink(negative expansion)deformation of the *** the new structural design,large NHE effects can be *** theoretical investigation and finite element analysis(FEA)were conducted to demonstrate the large negative expansion effects of such *** results showed that the effective NHE ratio of the metamaterial is dependent of the curvature of the curved ligament and the size of both the ligament and the connecting *** ultra-large NHE ratios about−80%for the 2D structure and−90%for the 3D version can be obtained by adopting the structural *** newly designed metamaterials have potential applications in medical and other fields.

关键词： Hydrogel-based metamaterial structural design negative hygroscopic expansion active deformation

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of the Self-shielded Shim Coil Combined with Target Points 16

Optimal Design of the Self-shielded Shim Coil Combined with ...

引用

16th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2023

作者： Wang, Kun Ma, Danyue Lu, Jixi Zhang, Xu Wang, Shuying Lu, Chenning Wang, Jing School of Instrumentation and Optoelectronic Engineering Beihang University Beijing China Hefei National Laboratory Hefei China Hangzhou Institute of National Extremely-weak Magnetic Field Infrastructure Hangzhou China Innovation Institute Beihang University Zhejiang Provincial Key Laboratory of Ultra-Weak Magnetic-Field Space and Applied Technology Hangzhou China Beijing Institute of Electronic System Engineering Beijing China

ISBN: (纸本)9798350327144

This research proposes a self-shielded saddle shim coil design technique, based on the magnetic field data of the target field points, to counterbalance the coupling effect of the magnetic shield on the coil in the utilization of atomic sensors. This coil is composed of two nested saddle coils: the main coil and the shielding coil. The optimization function, which characterizes the internal homogeneity of the magnetic field and attenuation of the external field, is determined by the magnitude of magnetic induction at both internal and external points of the coil. The NSGA-II optimization algorithm was then used to solve the geometrical parameters of the coil, with the optimization function serving as the optimization criterion to attain the parametric solution. Based on the proposed optimized method, a self-shielded coil was designed and tested in a cylindrical ferrite shield barrel. Results from both simulation and experimentation demonstrate a decrease in the coil constant due to the coupling effect of magnetic shield and coil from 58.96% to 0.54%, while the coil designed preserves the magnetic field uniformity in the central region in comparison to the classic saddle coil. This method is suitable for applications where the magnetic shield is combined with coils. © 2023 IEEE.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallelism or Fairness? How to Be Friendly for SSDs in Cloud Environments

Parallelism or Fairness? How to Be Friendly for SSDs in Clou...

引用

IEEE International Conference on Cluster Computing

作者： Yang Zhou Fang Wang Zhan Shi Dan Feng Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology Ministry of Education of China Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350358711

ISBN: (纸本)9798350358728

Modern SSDs achieve low latency and high throughput by utilizing multiple levels of SSD parallelism. Fairness is also a critical design consideration in cloud environments and has inspired great interest in recent years to study it. However, we find that excessive striving for SSD parallelism can inadvertently harm the SSD fairness due to the striped data layout. We observe from our experimental analysis that some common access patterns in cloud loads (e.g., high-intensity I/O) are not addressed by SSD parallelism, which can affect both SSD parallelism and fairness. In this paper, we analyze two address mapping policies with orthogonal characteristics from SSD parallelism and fairness perspectives. Based on extensive experiments and observations, we schedule a hybrid address mapping policy to achieve fairness of SSDs in cloud environments by distinguishing different I/O access modes and cold/hot data, while ensuring SSD performance. Experimental results on the latest block-level I/O traces show that our approach significantly improves performance and fairness by up to 77.3% and 62.8%, respectively, over the previous schemes with negligible cost. Meanwhile, it can also reduce the write amplification by 23.5% to 33.5%.

关键词： Schedules Layout Interference Parallel processing Predictive models Throughput data models Resource management Decision trees Low latency communication

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：