检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mao, Qianchen Li, Qiang Wang, Bingshu Zhang, Yongjun Dai, Tao Chen, C.L. Philip The School of Software Northwestern Polytechnical University Taicang Campus Suzhou215400 China The School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou510641 China

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder to restore the feature map. Firstly, the fast branch directly predicts a sparse map indicating potential small target locations (occupying only 0.5% area of the map). Secondly, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. Additionally, we design an lightweight DO-RepEncoder based on reparameterization with the Downsampling Orthogonality, which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models while achieving faster inference speed and fewer parameters. For example, on the IRSTD-1K dataset, SpirDet improves MIoU by 4.7 and has a 7× FPS acceleration compared to the previous state-of-the-art model. The code will be open to the public. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DeepVec: State-Vector Aware Test Case Selection for Enhancing Recurrent Neural Network

引用

IEEE Transactions on software engineering 2025年

作者： Jiang, Zhonghao Yan, Meng Huang, Li Sun, Weifeng Liu, Chao Sun, Song Lo, David Chongqing University School of Big Data and Software Engineering China Chongqing Normal University School of Computer and Information Science China Singapore Management University School of Information Systems Singapore

Deep Neural Networks (DNN) have realized significant achievements across various application domains. There is no doubt that testing and enhancing a pre-trained DNN that has been deployed in an application scenario is crucial, because it can reduce the failures of the DNN. DNN-driven software testing and enhancement require large amounts of labeled data. The high cost and inefficiency caused by the large volume of data of manual labeling, and the time consumption of testing all cases in real scenarios are unacceptable. Therefore, test case selection technologies are proposed to reduce the time cost by selecting and only labeling representative test cases without compromising testing performance. Test case selection based on neuron coverage (NC) or uncertainty metrics has achieved significant success in Convolutional Neural Networks (CNN) testing. However, it is challenging to transfer these methods to Recurrent Neural Networks (RNN), which excel at text tasks, due to the mismatch in model output formats and the reliance on image-specific characteristics. What’s more, balancing the execution cost and performance of the algorithm is also indispensable. In this paper, we propose a state-vector aware test case selection method for RNN models, namely DeepVec, which reduces the cost of data labeling and saves computing resources and balances the execution cost and performance. DeepVec selects data using uncertainty metric based on the norm of the output vector at each time step (i.e., state-vector), and similarity metric based on the direction angle of the state-vector. Because test cases with smaller state-vector norms often possess greater information entropy and similar changes of state-vector direction angle indicate similar RNN internal states. These metrics can be calculated with just a single inference, which gives it strong bug detection and model improvement capabilities. We evaluate DeepVec on five popular datasets, containing images and texts as well as commonl

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Jia, Ninghui Qu, Zhihao Ye, Baoliu Wang, Yanyan Hu, Shihong Guo, Song Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Nanjing211100 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Kowloon Hong Kong

In traditional centralized machine learning, transmitting raw data to a cloud center incurs high communication costs and raises privacy concerns. This is particularly challenging in mobile edge environments, where devices are dynamic and resource-constrained. Federated Learning (FL) addresses these issues by allowing devices to train models locally and upload parameters to a central server without sharing local data. However, limited wireless channel resources and dynamic transmission performance make communication overhead a major bottleneck of FL in mobile edge environments. Concerning this challenge, this survey provides a comprehensive summary of methods to improve communication efficiency in FL, focusing on: 1) minimizing communication complexity to reduce total transmission volume, 2) scheduling resources appropriately to improve training efficiency, 3) utilizing over-the-air computation (OTA) to integrate computation into communication for accommodating the computation/communication characteristics of FL in mobile edge environments. Thus, this work analyzes research from the perspective of convergence and data heterogeneity to reduce communication rounds by optimizing algorithm performance. We hope that this survey could offer insights into communication-efficient FL for future research. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Suppressing Beam Squint Effect For Near-Field Wideband Communication Through Movable Antennas

arXiv

引用

arXiv 2024年

作者： Zhu, Yanze Wu, Qingqing Liu, Yang Shi, Qingjiang Chen, Wen Department of Electronic Engineering Shanghai Jiao Tong University 200240 China School of Information and Communication Engineering Dalian University of Technology Dalian China School of Software Engineering Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China

In this correspondence, we study deploying movable antenna (MA) array in a wideband multiple-input-single-output (MISO) communication system, where near-field (NF) channel model is considered. To alleviate beam squint effect, we propose to maximize the minimum analog beamforming gain across the entire wideband spectrum by appropriately adjusting MAs’ positions, which is a highly challenging task. By introducing a slack variable and adopting the cutting-the-edge smoothed-gradient-descent-ascent (SGDA) method, we develop algorithms to resolve the aforementioned challenge. Numerical results verify the effectiveness of our proposed algorithms and demonstrate the benefit of utilizing MA array to mitigate beam squint effect in NF wideband system. © 2024, CC0.

关键词： Near field communication

来源：评论

学校读者我要写书评

暂无评论

Noise robust Mongolian speech data augmentation model structure 22

Noise robust Mongolian speech data augmentation model struct...

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： Zhiqiang, Ma Jiaqi, Sun Jinyi, Li Jiatai, Wang College of Data Science and Application Inner Mongolia University of Technology Huhhot010000 China Inner Mongolia Autonomous Region Software Service Engineering Technology Research Center Based on Big Data Huhhot010000 China

ISBN: (纸本)9781713876229

There is a lack of phonetic diversity in Mongolian corpus. Although manpower and funds spent on data collection can increase the number of phonetic sounds to some extent, the whole process needs a lot of time. data augmentation can solve the problem of data scarcity, but the environmental noise contained in the training data of the data augmentation model cannot be controlled, resulting in background noise in the augmentation speech. In this paper, a speech data augmentation method combining TTS and speech enhancement is proposed. Based on the speech spectrum graph, speech enhancement is carried out from two dimensions: frequency domain and time domain. Multiple experiments show that the qualified rate of Mongolian augmented speech reaches 70%, the CBAK and COVL of augmented speech decrease by 0.66 and 0.81, and WER and SER decrease by 2.75% and 2.05%, respectively. © 2023 China National Conference on Computational Linguistics.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

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

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware contrastive learning for selective classification 24

Confidence-aware contrastive learning for selective classifi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yu-Chang Wu Shen-Huan Lyu Haopu Shang Xiangyu Wang Chao Qian National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China and National Key Laboratory for Novel Software Technology Nanjing University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

xASTNN: Improved Code Representations for Industrial Practice

arXiv

引用

arXiv 2023年

作者： Xu, Zhiwei Chen, Yang Zhou, Min Cheng, Xi Zhao, Xibin Zhang, Hongyu KLISS BNRist School of Software Tsinghua University Beijing China School of Computer Science Fudan University Shanghai China VMware Beijing China School of Big Data and Software Engineering Chongqing University Chongqing China

The application of deep learning techniques in software engineering becomes increasingly popular. One key problem is developing high-quality and easy-to-use source code representations for code-related tasks. The research community has acquired impressive results in recent years. However, due to the deployment difficulties and performance bottlenecks, seldom these approaches are applied to the industry. In this paper, we present xASTNN, an eXtreme Abstract Syntax Tree (AST)-based Neural Network for source code representation, aiming to push this technique to industrial practice. The proposed xASTNN has three advantages. First, xASTNN is completely based on widely-used ASTs and does not require complicated data pre-processing, making it applicable to various programming languages and practical scenarios. Second, three closely-related designs are proposed to guarantee the effectiveness of xASTNN, including statement subtree sequence for code naturalness, gated recursive unit for syntactical information, and gated recurrent unit for sequential information. Third, a dynamic batching algorithm is introduced to significantly reduce the time complexity of xASTNN. Two code comprehension downstream tasks, code classification and code clone detection, are adopted for evaluation. The results demonstrate that our xASTNN can improve the state-of-the-art while being faster than the baselines. © 2023, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

***: Vertical and Horizontal Learning for Request Scheduling in Edge-Cloud Systems

***: Vertical and Horizontal Learning for Request Scheduling...

引用

IEEE International Conference on Communications (ICC)

作者： Xiaoyun Shi Yunfeng Zhao Chao Qiu Xiaofei Wang Xiuhua Li Wenyu Wang College of Intelligence and Computing Tianjin University Tianjin China School of Big Data & Software Engineering Chongqing University Chongqing China Paiou Cloud Computing (Shanghai) Co. Ltd. Shanghai China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

With the rapid development of Internet of Things (loT) device performance, edge-cloud systems are generating vast volumes of complex data. Meanwhile, the distributed and multi-layer structure of edge-cloud systems pose significant challenges to scheduling decision-making and convergence of the algorithm. In this paper, from a vertical and horizontal perspective of edge-cloud systems, we propose a deep reinforcement learning (DRL) algorithm called CrossLearning. We apply a curiosity-driven multi-agent learning method horizontally to accelerate the convergence speed of the algorithm. We introduce an inter-layer decision refinement mechanism vertically to address the challenge of inaccurate decision-making. We also refine the service types and levels to efficiently match the various application needs of users in the big data era. Finally, we implement a prototype system on a network hardware system and conduct experiments using real datasets. The evaluation shows that, in comparison to baseline methods, CrossLearning demonstrates significant im-provements in terms of time efficiency and load balance, with a notable enhancement in algorithm convergence speed.

关键词： Performance evaluation Learning systems System performance Decision making Prototypes big data Scheduling

来源：评论

学校读者我要写书评

暂无评论

FedVC: Virtual Clients for Federated Autonomous Driving With Imbalanced Label Distribution

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Yongquan Chen, Hongda Wang, Zhihui Kumar, Rahul Wang, Changmiao Zhejiang University of Finance and Economics School of Data Science Hangzhou310018 China Xi'an Jiaotong University School of Software Engineering Xi'an710049 China Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266510 China Ssv Pg College Department Of Mathematics Hapur245101 India Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning in autonomous driving safeguards the privacy of individual vehicles during collaborative training by avoiding the exchange of raw data. These vehicles often suffer from imbalanced label distribution, making the federated learning model developed from them critical for safety. Most current solutions addressing label imbalance in federated learning are oriented towards classification tasks. However, there is limited research focused on prediction tasks involving imbalanced datasets relevant to autonomous driving. To address the identified gap, we introduce an innovative peer-to-peer federated learning framework called FedVC. This framework includes the use of virtual clients to enhance the ability of the collaborative training process to recognize the global data distribution effectively. It strategically samples relevant segments of local data from various clients for each training round and controls the execution time for backpropagation associated with each virtual client. Importantly, FedVC constructs a global perspective by utilizing metadata from each client, thereby maintaining data privacy while overcoming the challenge of label imbalance in autonomous driving prediction tasks, all without the need to share any raw datasets. Experimental results demonstrate that FedVC outperforms classical FedAvg and the most recent methods at three steering angle prediction datasets with different levels of imbalanced label distribution. The source code is publicly available at https://***/aikedaerC/FedVC. © 1975-2011 IEEE.

关键词： Autonomous Driving data Imbalance Federated Learning Virtual Clients

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：