检索结果-内蒙古大学图书馆

Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking

IEEE Transactions on Signal Processing 2025年 73卷 1851-1861页

作者： Chen, Jun Liu, Lina Zhu, Tianyi Liu, Yong Dai, Guang Jiang, Yunliang Tsang, Ivor W. Zhejiang Normal University National Special Education Resource Center for Children with Autism Hangzhou311231 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China China Mobile Research Institute Beijing100032 China Zhejiang University Institute of Cyber-Systems and Control Hangzhou310027 China State Grid Corporation of China SGIT AI Lab China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Huzhou University School of Information Engineering Huzhou313000 China Centre for Frontier Artificial Intelligence Research A*STAR Singapore

This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by n agents forming an undirected and connected graph. However, the efficiency of distributed optimization is often hindered by communication bottlenecks. To mitigate this, we propose the Quantized Riemannian Gradient Tracking (Q-RGT) algorithm, where agents update their local variables using quantized gradients. The introduction of quantization noise allows our algorithm to bypass the constraints of the accurate Riemannian projection operator (such as retraction), further improving iterative efficiency. To the best of our knowledge, this is the first algorithm to achieve an O(1/K) convergence rate in the presence of quantization, matching the convergence rate of methods without quantization. Additionally, we explicitly derive lower bounds on decentralized consensus associated with a function of quantization levels. Numerical experiments demonstrate that Q-RGT performs comparably to non-quantized methods while reducing communication bottlenecks and computational overhead. © 1991-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Few Shot Contrastive Spectral Clustering with Meta Learning and Neighbor Mining

Few Shot Contrastive Spectral Clustering with Meta Learning ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Nongxiao Wang Xulun Ye Jieyu Zhao Qing Wang Department of Computer Science and Technology Ningbo University China Key Lab of Mobile Network Application Technology of Zhejiang Province Ningbo China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Spectral clustering is widely used in the field of unsupervised learning and has been successfully applied in various data analysis tasks. However, in practical scenarios, it’s common to get few labeled data at low cost, resulting limited labeled data in few categories, while the rest are completely unlabeled. Relying solely on the unsupervised clustering framework can’t leverage the existing supervised information. Using a supervised meta-learning paradigm alone poses challenges when dealing with the majority categories of completely unlabeled data. Therefore, we propose a few-shot contrastive spectral clustering combined with meta learning and neighbor mining framework (FCSMN). First we leverage few shot labeled information to obtain a meta-learning feature embedding with strong generalization capabilities, and acquire semantic feature spaces using an unsupervised contrastive learning model. Then, we mine neighbors in these two feature spaces separately and align them. Next, we jointly reinforce intra-cluster compactness and inter-cluster separability at both instance and cluster level. To satisfies the conditions of spectral clustering, we impose orthogonality constraints at the last layer. Experiments on three datasets demonstrate the effectiveness our proposed method.

关键词： Metalearning Costs Semantics Neural networks Contrastive learning Data augmentation Data mining

来源：评论

学校读者我要写书评

暂无评论

BREAKING SPEAKER RECOGNITION WITH PADDINGBACK

arXiv

引用

arXiv 2023年

作者： Ye, Zhe Yan, Diqun Dong, Li Shen, Kailai Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology China

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. However, human ears can easily be aware of these transformations, leading to suspicion. In this paper, we propose PaddingBack, an inaudible backdoor attack that utilizes malicious operations to generate poisoned samples, rendering them indistinguishable from clean ones. Instead of using external perturbations as triggers, we exploit the widely-used speech signal operation, padding, to break speaker recognition systems. Experimental results demonstrate the effectiveness of our method, achieving a significant attack success rate while retaining benign accuracy. Furthermore, PaddingBack demonstrates the ability to resist defense methods and maintain its stealthiness against human perception. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A 7nm-Based Decodable Self-Resetting Regfile Circuit 15

A 7nm-Based Decodable Self-Resetting Regfile Circuit

引用

15th IEEE International Conference on ASIC, ASICON 2023

作者： Zhao, Wanlong Zhang, Yuejun Ren, Mingze Wen, Liang Wang, Pengjun Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China Ningbo University Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China China Coast Guard Academy Department of Electronic Technology Ningbo China Wenzhou University College of Electrical and Electronic Engineering Wenzhou325035 China

ISBN: (纸本)9798350312980

This paper presents a novel design scheme for a decodable self-resetting Regfile circuit that aims to reduce the power consumption caused by massive data and high computing power. The scheme consists of three steps: first, it analyzes the working principle and the energy consumption process of the decoding circuit;second, it proposes a self-resetting decoding circuit structure that uses the clock to control the decoding state and automatically resets when the clock is low, thus avoiding the extra power consumption due to the inversion of the memory cell state during the non-working period of the decoding circuit;third, it implements a two-read, two-write, decodable self-resetting Regfile circuit using a full-custom design method under the TSMC 7nm FinFET process. The experimental results demonstrate that the circuit has an area of 5593μm2 and an energy-delay product of 0.41pJ•nS, and it can operate stably at 4GHz under various temperatures and process corner conditions. © 2023 IEEE.

关键词： 7nm process high speed low power consumption Regfile circuit

来源：评论

学校读者我要写书评

暂无评论

Research and Standardization Requirements for 5G network Peak Control technology in Video Transmission

Research and Standardization Requirements for 5G Network Pea...

引用

2022 ITU Kaleidoscope - Extended Reality - How to Boost Quality of Experience and Interoperability, ITU K 2022

作者： Deng, Zhiji Fu, Zhewei Liu, Ming Qu, Xiangyu Ding, Dong Ye, Qi Kong, Weisheng Wang, Fei Zhang, Jinyu Wang, Hui Lou, Jian Zhejiang Provincial Key Laboratory of Harmonized Application of Vision & Transmission China Zhejiang Dahua Technology Co. Ltd. China China Mobile Communications Corporation China

ISBN: (纸本)9789261361518

The 5G network peak control technology in video transmission scenarios is used to solve the problem of violent fluctuations in network peaks caused by the collision of I-frames (key frames) during multichannel video transmission. Based on the research of key technologies such as I-frame collision detection and network peak shift scheduling, through the Multiaccess Edge Computing (MEC) external interface, the network data and video management system is opened to effectively smooth the network peak during multichannel video transmission, and realize the number and bandwidth of 5G terminal access under 5G base stations. The improved utilization rate is conducive to the large-scale promotion of 5G video surveillance scenarios. © 2022 ITU.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Msqat: A Multi-Dimension Non-Intrusive Speech Quality Assessment Transformer Utilizing Self-Supervised Representations

SSRN

引用

SSRN 2023年

作者： Shen, Kailai Yan, Diqun Dong, Li Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China

Convolutional neural networks (CNNs) have been widely utilized as the main building block for many \textit{non-intrusive} speech quality assessment (NISQA) methods. A new trend is to add a self-attention mechanism based on CNN to better capture long-term global content. However, it is not clear whether the pure attention-based network is sufficient to obtain good performance in NISQA. To this end, a framework named \textbf{M}ulti-dimension \textit{non-intrusive} \textbf{S}peech \textbf{Q}uality \textbf{A}ssessment \textbf{T}ransformer (MSQAT) is proposed. To strengthen the interactions of various speech regions between local and global, three multi-dimensional modules are devised. Additionally, speech quality varies not only in different frames, but also in different frequencies. Thus, a two-branch structure is designed to better evaluate the quality of speech. Experimental results demonstrate that the proposed MSQAT has state-of-the-art performance on three standard datasets (NISQA Corpus, Tencent Corpus, and PSTN Corpus). © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Non-Intrusive Speech Quality Assessment: A Survey

SSRN

引用

SSRN 2023年

作者： Shen, Kailai Yan, Diqun Hu, Jing Ye, Zhe Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China

Speech quality is a critical consideration for applications such as speech enhancement, coding, transmission, and synthesis. Accurately evaluating the quality of degraded speech without a reference is particularly challenging. As a result, non-intrusive speech quality assessment has been extensively researched due to its efficiency and ease of deployment. This survey comprehensively reviews these studies. Commonly used speech quality assessment databases are reviewed, as they serve as validation sets for objective metrics. Non-intrusive speech quality assessment methods are categorized and reviewed, and the performance of state-of-the-art and classical speech quality methods is compared. The survey presents an overview of classic algorithms and recent advancements in the field of non-intrusive speech quality assessment. © 2023, The Authors. All rights reserved.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Fast Crop Pest Detection Using Lightweight Feature Extraction and Knowledge Distillation

Fast Crop Pest Detection Using Lightweight Feature Extractio...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ze Yang Xianliang Jiang Guang Jin Junkai Huang Jie Bai Dingxin Yu Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China

Pest detection is critical for achieving effective pest control. However, the current deep learning-based pest detection algorithm is unsuitable for deployment on resource-limited edge devices due to its extensive computation and long inference time. Although lightweight models have been widely used for practical detection, their insufficient feature extraction capability leads to a decline in detection accuracy. This paper proposes a fast algorithm for crop pest detection based on lightweight feature extraction and knowledge distillation. Firstly, we introduce partial convolution and propose a lightweight feature extraction module, C3Faster, which reduces the model's computation and speeds up model inference while ensuring effective feature extraction. Secondly, we use knowledge distillation to improve the model's detection accuracy by using teacher networks to assist in training. Finally, we created a dataset, CropPest6, consisting of six crop pest categories and conducted experiments. The experimental results demonstrate that our method reduces the detection time, number of parameters, and computation by 17%, 38%, and 44%, respectively, compared to the baseline model. Furthermore, our method achieves 93.9% Precision, 93.6% Recall, and 97.5% mean Average Precision (mAP), demonstrating its practical suitability for fast crop pest detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing source code summarization from structure and semantics

Enhancing source code summarization from structure and seman...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Xurong Lu Jun Niu Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China Zhejiang Engineering Research Center of Advcanced Mass Spectrometry and Clinical Application Ningbo China

Source code summarization aims to generate concise and high-quality natural language descriptions for code snippets. High-quality code summaries can help developers better understand source codes. Researchers have made great efforts to generate more accurate summaries; however, due to the lack of preservation of source code structure and semantics, previous approaches have struggled to generate summaries that accurately describe the functionality or other major characteristics of codes. In this paper, we propose a novel approach called Code Structure and Semantic Fusion (CSSF) for automatically generating summaries for source code. CSSF can utilize both the structural and semantic information of source codes. To achieve this, we extract the overall structure of the Abstract Syntax Tree (AST) by expanding the AST and using a heterogeneous graph attention network. Furthermore, we use an additional sequence model to obtain the semantic information of the code fragment. Finally, we fuse the two kinds of information through a novel modality fusion method. We evaluate our approach on a widely used Java dataset; experimental results confirm that our approach outperforms existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Band Sleeve Dipole Antenna for 2.4/5/6 GHz WLAN application 15

A Multi-Band Sleeve Dipole Antenna for 2.4/5/6 GHz WLAN Appl...

引用

15th International Conference on Microwave and Millimeter Wave technology, ICMMT 2023

作者： Yan, Fu-Gui Dong, Xiao-Nan Fang, Yong-Jun Wang, Ya-Xing Deng, Zhi-Ji Zhejiang Dahua Technology Co. Ltd. Zhejiang Provincial Key Laboratory of Harmonized Application of Vision & Transmission Zhejiang Hangzhou310053 China Shenzhen University Guangdong Provincial Mobile Terminal Microwave and Millimeter-Wave Antenna Engineering Research Center Guangdong-Hong Kong Joint Lab. Bdic Shenzhen518060 China

ISBN: (纸本)9798350338874

The paper proposes a novel sleeve dipole antenna design that effectively covers three WiFi frequency bands with excellent radiation patterns. The antenna consists of two metal cylinders and two sleeves with different radius and lengths and has an impedance bandwidth that covers the 2.4 GHz, 5 GHz, and 6 GHz WiFi frequency bands. Notably, the antenna's radiation patterns are almost omnidirectional, while remaining stable within the working bandwidth. The antenna can operate across multiple bands, providing greater flexibility in frequency selection for wireless data transmission. Overall, the proposed antenna design is suitable for various wireless communication systems. © 2023 IEEE.

关键词： Dipole antennas

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：