检索结果-内蒙古大学图书馆

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

FDAIMC: A Fully-Differential Analog In-Memory-Computing for MAC in MRAM with Accuracy Calibration Under Process and Voltage Variation

FDAIMC: A Fully-Differential Analog In-Memory-Computing for ...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Xiangyu Li Weichong Chen Ruida Hong Jinghai Wang Ningyuan Yin Zhiyi Yu School of Microelectronics Science and Technology Sun Yat-sen University China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Analog in-memory-computing (AIMC) is adopted extensively in non-volatile memory for multibit multiply-and-accumulate (MAC) operation. However, the low-on/off-ratio feature of magnetic tunnel junction (MTJ) impedes a high-performance AIMC macro based on spin transfer torque magnetic random access memory (STT-MRAM). Secondly, because of the uncertainty feature of a mixed-signal system under process and voltage variation, a calibration support is indispensable. Moreover, the incompatibility between a nonlinear analog signal and a linear digital signal hinders accurate computation and calibration support. To overcome these challenges, this work proposes a STT-MRAM-AIMC macro featuring: 1) a 2-level-differential cell array and a linear computing scheme with a calibration support in analog domain; 2) an analog-digital-conversion (ADC) system, including a slew-rate-independent voltage-to-time converter (SRIVTC) scheme and a self-triggered time-to-MAC value converter (STTMC) scheme; 3) a compact layout design for high area efficiency. Finally, an average accuracy of 95.44% is obtained under the TT&0.9V corner. By using the calibration strategy, the average accuracy of 97.8% and 88.6% are obtained under FF&0.945V and SS&0.855V separately, with over 30% enhancement. Furthermore, a 1.64~21.18 times area FoM than state of the art is obtained. An energy efficiency of 87.2~312.4 TOPS/W is obtained.

关键词： Accuracy Uncertainty Torque Nonvolatile memory Magnetic separation Random access memory Magnetic domains Voltage Calibration Magnetic tunneling

来源：评论

学校读者我要写书评

暂无评论

A Time-Borrowing Method for High-Performance Bundled-Data Asynchronous Circuits

A Time-Borrowing Method for High-Performance Bundled-Data As...

引用

IEEE International Symposium on Quality Electronic Design

作者： Bohan Wang Zeyang Xu Lingfeng Zhou Huiyao Wang Jinghai Wang Zhiyi Yu Shanlin Xiao School of Microelectronics Science and Technology Sun Yat-sen University China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems China

ISBN: (数字)9798331509422

ISBN: (纸本)9798331509439

Asynchronous circuits are increasingly being used in Very Large Scale Integration (VLSI) to address power consumption challenges. The performance of existing asynchronous circuits is still constrained by critical paths, and the phase shift induced by the asynchronous handshake logic exacerbates the adverse effects caused by critical path. Latches have the potential to address this issue due to their timing borrowing characteristics, and they consume lower power compared to flip-flops (FFs). However, most existing asynchronous circuits are only geared towards flip-flop-based designs and cannot fully capitalize on the advantages of latches. In this article, we propose a time-borrowing method for asynchronous circuits, including a novel dual-phase lightweight asynchronous controller (DPLAC) and a margin-aware asynchronous control method, which can fully exploit the low-power and time-borrowing characteristics of latches. To verify this method, we designed an asynchronous RISC-V processor with dual-phase latches on the TSMC 65-nm process. Compared to its synchronous version, when operating at the extreme frequency, the asynchronous processor achieves a 15.8% increase in speed (from 227.3 to 263.2MHz) while reducing power consumption by 28.71%.

关键词： Latches Power demand Very large scale integration Timing Logic Frequency synchronization Asynchronous circuits Flip-flops

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

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detection

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detect...

引用

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

作者： Wang, Guangjin Wang, Bao Xu, Fuyong Zhu, Zhenfang Wang, Peipei Wang, Ru Liu, Peiyu School of Information Science and Engineering Shandong Normal University Jinan China School of Information Science and Electrical Engineering Shandong Jiao Tong University Jinan China Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9798350368741

Multimodal sarcasm detection aims to identify whether utterances express sarcastic intentions contrary to their literal meaning based on multimodal information. However, existing methods fail to explore the model's "ability to understand" the semantics expressed by sentences in the image context from semantic diversity perspectives. In this paper, we propose a multi-view semantic awareness method, which concretizes semantics from multiple perspectives to improve the model's ability to capture different semantic features. Specifically, two learnable prefixes are attached to the text representation respectively to construct semantic representations from both the literal meaning and sarcastic intention perspectives. Then, image-text information is further fused through cross-attention to guide the semantic representation of different perspectives in the image context. Finally, the semantics expressed by prefixes are strengthened through KL divergence, thereby encouraging the model to capture two distinctive semantic features. Experiments on benchmark datasets demonstrate the effectiveness of our method. © 2025 IEEE.

关键词： KL divergence multi-view semantic representation multimodal sarcasm detection semantic representation enhancement

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：