检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

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

Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Tian, Zhuojun Zhang, Zhaoyang Li, Yiwei Bennis, Mehdi Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China University of Oulu Center for Wireless Communications Oulu90014 Finland State Key Laboratory of Industrial Control Technology Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multimodal Communication Networks and Intelligent Information Processing Hangzhou310027 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China

To jointly tackle the challenges of data and node heterogeneity in decentralized learning, we propose a distributed strong lottery ticket hypothesis (DSLTH), based on which a communication-efficient personalized learning algorithm is developed. In the proposed method, each local model is represented as the ‌Hadamard product of global real-valued parameters and a personalized binary mask for pruning. The local model is learned by updating and fusing the personalized binary masks while the real-valued parameters are fixed among different agents. To further reduce the complexity of hardware implementation, we incorporate a group sparse regularization term in the loss function, enabling the learned local model to achieve structured sparsity. Then, a binary mask aggregation algorithm is designed by introducing an intermediate aggregation tensor and adding a personalized fine-tuning step in each iteration, which constrains model updates towards the local data distribution. The proposed method effectively leverages the relativity among agents while meeting personalized requirements in heterogeneous node conditions. We also provide a theoretical proof for the DSLTH, establishing it as the foundation of the proposed method. Numerical simulations confirm the validity of the DSLTH and demonstrate the effectiveness of the proposed algorithm. © 2015 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

LSU-NET: LIGHTWEIGHT AUTOMATIC ORGANS SEGMENTATION NETWORK FOR MEDICAL IMAGES

arXiv

引用

arXiv 2025年

作者： Ding, Yujie Teng, Shenghua Li, Zuoyong Chen, Xiao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou350121 China

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Segmentation of CAD models using hybrid representation

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 188-202页

作者： Claude UWIMANA Shengdi ZHOU Limei YANG Zhuqing LI Norbelt MUTAGISHA Edouard NIYONGABO Bin ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peace-Bay Academy of Virtual Reality Shenyang 110004China China Aerospace Systems Engineering Corporation Beijing 100070China Department of Signal and Information Processing Beihang UniversityBeijing 100191China Department of Computer Science University of SherbrookeSherbrooke J1C0A1Canada

In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD *** previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point ***,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological ***,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation *** combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh *** complex CAD models,model segmentation is crucial for model retrieval and *** partial retrieval,it aims to segment a complex CAD model into several simple *** first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh *** second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD *** combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object *** study uses the Fusion 360 Gallery *** results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.

关键词： B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net

来源：评论

学校读者我要写书评

暂无评论

Adaptive symbiotic graph convolutional network

引用

Neurocomputing 2025年 637卷

作者： Zhou, Lin Xiao, Yuzhi Ye, Zhonglin Zhao, Haixing Liu, Zhen School of Computer Qinghai Normal University Qing Hai Xining810008 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qing Hai Xining810008 China Key Laboratory of Tibetan Information Processing Ministry of Education Qing Hai Xining810008 China Qinghai Provincial Key Laboratory of Tibetan Information Processing and Machine Translation Qing Hai Xining810008 China of Engineering Nagasaki Institute of Applied Science Kyushu Nagasaki851-0193 Japan

Within the intrinsic fabric of graph and network data, the latent reciprocity between network nodes forms a profound symbiotic relationship. Traditional graph neural networks struggle to adaptively parse and integrate multi-source features when learning these symbiotic relationships. To address this challenge, we propose a novel Adaptive Symbiotic Graph Convolutional Network (ASGCN) for semi-supervised node classification tasks. First, The initial contribution of this investigation is the introduction of a multi-scale feature convolution module, which enables the extraction of hierarchical features at varying scales and the construction of k-nearest neighbor graphs. This facilitates the deepening of the symbiotic features of nodes. Second, a symbiotic co-convolution module is put forth as a means of reinforcing the profound interdependence inherent to symbiotic relationships. Finally, an adaptive dynamic feature selection mechanism is introduced to flexibly respond to data characteristics, effectively identifying and fusing the most influential features in the processing information flow. Experimental results demonstrate that ASGCN exhibits significant advantages in deeply analyzing and integrating the intrinsic attributes of nodes with graph structural relationships, thereby improving performance in node classification tasks. © 2025 Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷

作者： Wang, Jiahui Xu, Qin Jiang, Bo Luo, Bin The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China The Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

The transductive Few-shot Learning (FSL) mostly employs either prototype learning or label propagation methods to generalize to new classes by using the information of all query samples. However, existing methods have several main limitations. First, the prototype methods mainly focus on support samples which fail to fully exploit the relationships of query samples. Second, existing label propagation methods are generally not effective for the class-imbalanced problem. Third, existing works usually optimize the learnable parameters during inference which significantly reduces the efficiency of existing methods. To address these limitations, this article proposes an efficient and robust method for transductive FSL problem, termed Prototype-based Soft-label Propagation (PSLP), which combines the prototype learning and label propagation together for FSL problem. In our proposed method, first, the soft-label presentation for each query sample is estimated by leveraging prototypes. Then, the soft-label propagation is conducted on the learned query-support graph and the prototype representation is rectified. Both steps are conducted progressively for boosting the performance. Moreover, to learn effective prototypes for soft-label estimation and the desirable query-support graph for soft-label propagation, we design a new joint message passing scheme to learn the sample presentation and relational graph jointly. The PSLP method is parameter-free and can be implemented very efficiently. The experiments conducted on four popular benchmarks show that our method achieves competitive results on both balanced and imbalanced settings compared to the state-of-the-art methods. The code is released at https://***/mobulan/PSLP. © 2025 Copyright held by the owner/author(s).

关键词： Few-shot learning Transductive learning Message passing Label propagation

来源：评论

学校读者我要写书评

暂无评论

Port-controllable routing of orbital angular momentum modes using a rotatable diffractive neural network

引用

Science China(Physics,Mechanics & Astronomy) 2025年第06期Mechanics & Astronomy) .卷 158-167页

作者： Junmin Liu Jiafu Chen Qingji Zeng Zemin Liang Xinping Wu Xin Zhao Jiangnan Xiao Huapeng Ye Ze Dong Dianyuan Fan Shuqing Chen Institute of Microscale Optoelectronics Shenzhen University College of New Materials and New Energies Shenzhen Technology University Terahertz Technology Innovation Research Institute Shanghai Key Laboratory of Modern Optical System Terahertz Science Cooperative Innovation Center School of Optical-Electrical Computer Engineering University of Shanghai for Science and Technology Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University School of Information and Electronics Beijing Institute of Technology

Orbital angular momentum(OAM) modes provide an additional orthogonal physical dimension, offering transformative potential for enhancing optical communication capacity. Despite significant progress in mode multiplexing, the development of robust communication networks faces persistent challenges, particularly in effectively routing and controlling these multiplexed channels among network nodes. To tackle these dilemmas, we propose a rotatable diffractive neural network(R-DNN) strategy and demonstrate its capability for port-controllable OAM mode routing. By leveraging the correlation between the orthogonal evolution of OAM modes in free space and phase modulations during propagation, the R-DNN precisely shapes the spatial evolution of mode fields through multiple rotatable phase layers, enabling efficient routing to specific output ports. This approach exploits the interaction of secondary wavelets with the relative states of the rotatable layers, allowing on-demand control of mode evolution paths and enhancing routing flexibility. As a proof of concept, we developed a tri-functional router that successfully directs three OAM modes to individually controllable output ports. This router achieves an average intermode crosstalk of less than-16.4 dB across three functional states, one-dimensional, two-dimensional, and cross-connected switching, while supporting the routing of 5.85 Tbit/s quadrature phase-shift keying signals. These results highlight the R-DNN's effectiveness in achieving precise and controllable OAM mode manipulation, paving the way for advanced applications in mode-multiplexed communication networks and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cache Periscope: Gain insights into the global epidemic of malicious domains through DNS Cache

引用

computer Networks 2025年 265卷

作者： Wang, Yabo Sun, Jiakun Xiao, Ruizhi Li, Weilong Jin, Shuyuan School of Computer Science and Engineering Sun Yat-sen University Guangzhou510000 China Guangdong Provincial Key Laboratory of Information Security Technology Guangzhou510000 China MoE Key Laboratory of Information Technology Sun Yat-sen University Guangzhou510000 China

Domain names are often abused for various harmful and illegal activities. To mitigate these threats, security practitioners have proposed detecting malicious domains based on features such as domain name resolution data, semantic attributes, website appearance, and website correlations. Although these techniques have achieved notable results, they remain relatively passive in countering malicious activities. In this paper, we present a large-scale measurement study of the global epidemic of malicious domain names on open resolvers using cache probing techniques. We propose a modified probing method designed for large-scale domain access estimation. Leveraging this method, we examine the access patterns of malicious domains under open resolvers, which are widely deployed and utilized across the Internet, aiming to map the distribution of malicious activities based on the geographic location of open resolvers. Additionally, to the best of our knowledge, we are the first to propose using domain name top lists to estimate the volume of resolver users, which reflects the potential influence of a resolver. The weights of the estimated user volumes are further validated by real DNS traffic. By integrating these two methods, we evaluate the potential impact of malicious domains and conduct extensive measurements and analyses of malicious domain activities on open resolvers worldwide. Our findings reveal the regional distribution of malicious campaigns and provide insights into the global epidemic of malicious domains. Our measurement results demonstrate that practitioners can actively collect threat intelligence using the proposed techniques, gain insights into the current Internet threats, and implement more proactive measures to combat malicious campaigns. © 2025 Elsevier B.V.

关键词： Cache probing Domain name system Malicious domain Open resolver Threat analysis

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：