检索结果-内蒙古大学图书馆

Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning

Chinese Journal of Electronics 2025年第1期34卷 98-113页

作者： Hengmin Zhang Jian Yang Wenli Du Bob Zhang Zhiyuan Zha Bihan Wen School of Electrical and Electronic Engineering Nanyang Technological University School of Computer Science and Engineering Nanjing University of Science and Technology School of Information Science and Engineering East China University of Science and Technology Department of Electrical and Computer Engineering University of Macau

Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.

关键词： Learning systems Image recognition Minimization Computational efficiency Complexity theory Matrix decomposition Optimization Image reconstruction Singular value decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

SSA: semantic structure aware inference on CNN networks for weakly pixel-wise dense predictions without cost

引用

Frontiers of computer science 2025年第2期19卷 1-10页

作者： Yanpeng SUN Zechao LI School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210014China

The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps(CAMs)to generate pseudo masks as ***,existing methods often incorporate trainable modules to expand the immature class activation maps,which can result in significant computational overhead and complicate the training *** this work,we investigate the semantic structure information concealed within the CNN network,and propose a semantic structure aware inference(SSA)method that utilizes this information to obtain high-quality CAM without any additional training ***,the semantic structure modeling module(SSM)is first proposed to generate the classagnostic semantic correlation representation,where each item denotes the affinity degree between one category of objects and all the ***,the immature CAM are refined through a dot product operation that utilizes semantic structure ***,the polished CAMs from different backbone stages are fused as the *** advantage of SSA lies in its parameter-free nature and the absence of additional training costs,which makes it suitable for various weakly supervised pixel-dense prediction *** conducted extensive experiments on weakly supervised object localization and weakly supervised semantic segmentation,and the results confirm the effectiveness of SSA.

关键词： class attention maps semantic structure weaklysupervised object localization weakly-supervised semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

A recover-then-discriminate framework for robust anomaly detection

引用

science China(Information sciences) 2025年第4期68卷 300-318页

作者： Peng XING Dong ZHANG Jinhui TANG Zechao LI School of Computer Science and Engineering Nanjing University of Science and Technology Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology

Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical *** paper analyzes two fundamental failure cases in the baseline AD model and identifies key reasons that limit the recognition accuracy of existing approaches. Specifically, by Case-1, we found that the main reason detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel recover-then-discriminate(ReDi) framework for *** takes a self-generated feature map(e.g., histogram of oriented gradients) and a selected prompted image as explicit input information to address the identified in Case-1. Additionally, a feature-level discriminative network is introduced to amplify abnormal differences between the recovered and input representations. Extensive experiments on two widely used yet challenging AD datasets demonstrate that ReDi achieves state-of-the-art recognition accuracy.

关键词： recovery network HOG prompt discriminative network self-correlation loss anomaly detection

来源：评论

学校读者我要写书评

暂无评论

YOLO-LFD: A Lightweight and Fast Model for Forest Fire Detection

引用

computers, Materials & Continua 2025年第2期82卷 3399-3417页

作者： Honglin Wang Yangyang Zhang Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Electrical&Computer Engineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA

Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction network. Secondly, we design and implement the Lightweight Faster Implementation of Cross Stage Partial (CSP) Bottleneck with 2 Convolutions (C2f-Light) and the CSP Structure with 3 Compact Inverted Blocks (C3CIB) modules to replace the traditional C3 modules. This optimization enhances deep feature extraction and semantic information processing, thereby significantly increasing inference speed. To enhance the detection capability for small fires, the model employs a Normalized Wasserstein Distance (NWD) loss function, which effectively reduces the missed detection rate and improves the accuracy of detecting small fire sources. Experimental results demonstrate that compared to the baseline YOLOv5s model, the YOLO-LFD model not only increases inference speed by 19.3% but also significantly improves the detection accuracy for small fire targets, with only a 1.6% reduction in overall mean average precision (mAP)@0.5. Through these innovative improvements to YOLOv5s, the YOLO-LFD model achieves a balance between speed and accuracy, making it particularly suitable for real-time detection tasks on mobile and embedded devices.

关键词： Forest fire detection YOLOv5 lightweight small object detection

来源：评论

学校读者我要写书评

暂无评论

Clustered Reinforcement Learning

引用

Frontiers of computer science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Motion-Enhanced Matching Framework for Few-Shot Action Recognition

引用

IEEE Transactions on Multimedia 2025年 27卷 2450-2462页

作者： Gao, Hailiang Xie, Guo-Sen Yan, Rui Cui, Qiongjie Qu, Hongyu Shu, Xiangbo Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University Department of Computer Science and Technology Nanjing210023 China

Few-Shot Action Recognition (FSAR) aims to recognize novel class action with limited annotated training data from the same class. Most FSAR methods subconsciously follow the few-shot image classification solutions by solely focusing on appearance-level matching between support and query videos, such as part-level matching, frame-level matching, and segment-level matching. However, these methods, almost always, have two main limitations: 1) generally ignore the relationship among these part-, frame- and segment-level features and 2) may mismatch the same class actions under fast-term and slow-term dynamics. To this end, we present a novel Hierarchical Motion-enhanced Matching (HM{^{2}}) framework to hierarchically learn the relation-aware multi-modal features, and jointly promote the multi-modal matching, including appearance-level matching on segments, frames, and parts, as well as the motion-level matching on dynamics. Specifically, we first propose a new Hierarchical Tokenizer (HT) to learn multi-modal features, namely utilizing a hierarchical Transformer to learn appearance-level features, along with a Slow-Fast Aware Motion (SFAM) strategy to learn motion-level features covering fast- and slow-term dynamics. Next, we propose a new Relation-aware Matcher (RM) to match the multi-modal features, by leveraging a Hierarchical Relational Graph Convolutional Network (H-RGCN) to capture the relationship among these appearance-level features. Further, a Dual Sample-to-Class Matching (DSCM) strategy is proposed to measure the bidirectional similarities among appearance- and motion-modal features by sample-to-class matching and class-to-sample matching. Extensive experiments on four golden FSAR datasets demonstrate significant performance improvements of HM2 compared with the state-of-the-art methods. © 1999-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Object Detection Algorithm for Foggy Traffic Scenarios

引用

computers, Materials & Continua 2025年第2期82卷 2451-2474页

作者： Honglin Wang Zitong Shi Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Electrical&Computer Engineering University of Illinois at Urbana ChampaignUrbanaIL 61801USA

In foggy traffic scenarios, existing object detection algorithms face challenges such as low detection accuracy, poor robustness, occlusion, missed detections, and false detections. To address this issue, a multi-scale object detection algorithm based on an improved YOLOv8 has been proposed. Firstly, a lightweight attention mechanism, Triplet Attention, is introduced to enhance the algorithm’s ability to extract multi-dimensional and multi-scale features, thereby improving the receptive capability of the feature maps. Secondly, the Diverse Branch Block (DBB) is integrated into the CSP Bottleneck with two Convolutions (C2F) module to strengthen the fusion of semantic information across different layers. Thirdly, a new decoupled detection head is proposed by redesigning the original network head based on the Diverse Branch Block module to improve detection accuracy and reduce missed and false detections. Finally, the Minimum Point Distance based Intersection-over-Union (MPDIoU) is used to replace the original YOLOv8 Complete Intersection-over-Union (CIoU) to accelerate the network’s training convergence. Comparative experiments and dehazing pre-processing tests were conducted on the RTTS and VOC-Fog datasets. Compared to the baseline YOLOv8 model, the improved algorithm achieved mean Average Precision (mAP) improvements of 4.6% and 3.8%, respectively. After defogging pre-processing, the mAP increased by 5.3% and 4.4%, respectively. The experimental results demonstrate that the improved algorithm exhibits high practicality and effectiveness in foggy traffic scenarios.

关键词： Deep learning object detection foggy scenes traffic detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Enhancing the spatter-removal rate in laser powder-bed fusion using a gas-intake system with dual inlets

引用

Journal of Zhejiang university-science A(Applied Physics & engineering) 2025年第3期26卷 252-265页

作者： Xin TIAN Junwei ZHONG Youwen YANG Chaolei ZHANG Long ZHAO School of Mechanical and Electrical Engineering Jiangxi University of Science and TechnologyGanzhou341000China College of Engineering and Applied Science Nanjing UniversityNanjing210089China

Mounds of spatter are generated in laser powder-bed fusion(L-PBF)additive manufacturing,which reduces build quality and laser *** to the lack of supplemental airflow above the chamber,the conventional build chamber with a single gas inlet exhibits a pronounced tendency for gas to flow upward near the *** phenomenon results in the formation of a large vortex within the build *** vortex leads to the chaotic motion trajectory of the spatter in the build *** design defects of the existing build chamber based on dual gas inlets are shown in this *** established a coupled computational fluid dynamics-discrete phase model(CFD-DPM)model to optimize the build chamber by adjusting the position and structure of the second gas *** homogeneity of the flow is increased with a distance of 379 mm between the two inlets and a wider-reaching second *** Coanda effect is also crucial in the spatter-removal *** Coanda effect is reduced by modifying the right sidewall of the build chamber and increasing the pressure difference between the inlet and ***,we found that the spatter-removal rate rose from 8.9%to 76.1%between the conventional build chamber with a single gas inlet and the optimized build chamber with two gas inlets.

关键词： Laser powder-bed fusion(L-PBF) Computational fluid dynamics(CFD) Flow field simulation Structural optimization Coanda effect

来源：评论

学校读者我要写书评

暂无评论

PosParser: A Heuristic Online Log Parsing Method Based on Part-of-Speech Tagging

引用

IEEE Transactions on Big Data 2025年第3期11卷 1334-1345页

作者： Jiang, Jinzhao Fu, Yuanyuan Xu, Jian Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

Log parsing, the process of transforming raw logs into structured data, is a key step in the complex computer system's intelligent operation and maintenance and therefore has received extensive attention. Among all log parsing methods, heuristic log parsing methods are lightweight and can work in a streaming mode to well meet the real-time parsing requirements. However, the existing log representations used in the heuristic log parsing methods are not powerful in distinguishing log messages, which leads to low parsing accuracy and weak generality. Inspired by trigger word extraction of the event detection task in natural language processing (NLP), this paper proposes an online log parser, named PosParser, which employs the part-of-speech (PoS) tagging to extract a function token sequence (FTS) as the log message representation, and then identify event templates of log messages through the FTS. Experimental results on sixteen logs from real systems demonstrate that the FTS is powerful in distinguishing log messages from different event templates, and PosParser not only performs better in terms of parsing accuracy than state-of-the-art methods but is also comparable to them in efficiency. © 2015 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Label Distribution Learning

引用

IEEE Transactions on Big Data 2025年第3期11卷 1221-1234页

作者： Wu, Haitao Li, Weiwei Jia, Xiuyi Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

Label distribution learning (LDL) suffers from the dilemma of insufficient target data in real-world applications, while domain adaptation (DA) seems to be able to provide a solution. However, most existing methods of DA, assuming that the instances can correspond to the explicit class information, are devoted only to classification but not to LDL. We argue that indiscriminately applying such DA methods might cause performance degradation in LDL tasks. In this paper, we propose LDL-DA, a novel algorithm dedicated to supervised domain adaptation for label distribution learning, which jointly learns a shared encoding representation from two aspects: 1) contrastive alignment of scarce supervised target data, and 2) minimizing the distance between prototypes of the same label combination. Experiments show that LDL-DA outperforms existing DA methods adapted to LDL, and provides early positive results in DA for LDL. To the best of our knowledge, this paper is the first research on DA for LDL. © 2015 IEEE.

关键词： Contrastive Learning

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：