检索结果-内蒙古大学图书馆

Subclass consistency regularization for learning with noisy labels based on contrastive learning

NEUROCOMPUTING 2025年 614卷

作者： Sun, Xinkai Zhang, Sanguo Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China

A prominent effect of label noise on neural networks is the disruption of the consistency of predictions. While prior efforts primarily focused on predictions' consistency at the individual instance level, they often fell short of fully harnessing the consistency across multiple instances. This paper introduces subclass consistency regularization (SCCR) to maximize the potential of this collective consistency of predictions. SCCR mitigates the impact of label noise on neural networks by imposing constraints on the consistency of predictions within each subclass. However, constructing high-quality subclasses poses a formidable challenge, which we formulate as a special clustering problem. To efficiently establish these subclasses, we incorporate a clustering-based contrastive learning framework. Additionally, we introduce the Q-enhancing algorithm to tailor the contrastive learning framework, ensuring alignment with subclass construction. We conducted comprehensive experiments using benchmark datasets and real datasets to evaluate the effectiveness of our proposed method under various scenarios with differing noise rates. The results unequivocally demonstrate the enhancement in classification accuracy, especially in challenging high-noise settings. Moreover, the refined contrastive learning framework significantly elevates the quality of subclasses even in the presence of noise. Furthermore, we delve into the compatibility of contrastive learning and learning with noisy labels, using the projection head as an illustrative example. This investigation sheds light on an aspect that has hitherto been overlooked in prior research efforts.

关键词： Deep learning Image classification Noisy label Consistency regularization Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Lightweight Perceptron for Cloud–Edge Collaborative Predictive Maintenance of Online Service Systems

引用

IEEE Internet of Things Journal 2025年第9期12卷 12640-12657页

作者： Zhang, Linzi Shi, Yong Wang, Donghan Communication University of China School of Economics and Management Beijing100024 China Chinese Academy of Sciences Research Center on Fictitious Economy and Data Science Key Laboratory of Big Data Mining and Knowledge Management Beijing100190 China

In the era of expanding cloud–edge online service systems, predictive maintenance (PdM) based on key performance indicators (KPIs), such as CPU utilization, response rate, and network bandwidth, is essential for system operational reliability and security. Traditional data-driven PdM approaches for cloud–edge services often monitor individual indicators in isolation, neglecting their interrelationships. Although convolutional modules have been utilized for collaborative representation learning of localized high-dimensional KPIs, the high-computational complexity of CNNs and the limited kernel size hinder their efficacy in modeling high-dimensional, time-sensitive KPIs. To address these challenges, we propose a lightweight multichannel multilayer perceptron (MCMLP) framework for collaborative PdM. This framework enables efficient pointwise manipulation to capture inner-indicator hidden patterns within KPIs sequences without relying on grid-based convolution. Our MCMLP enhances locality through a two-stage dual-channel feature extraction process that captures spatial and temporal dependencies, integrating inner-indicator and cross-timeline features. The proposed MCMLP can also be easily plugged into existing CNN-based detectors as a substitute, offering a computationally economical alternative. Empirical results in real-world KPI data from various cloud–edge service scenarios demonstrate that MCMLP significantly outperforms traditional CNN-based methods, with a roughly 22% reduction in training time at a 95% confidence level (α = 0.05 ). This study also provides actionable insights for deploying MCMLP in cloud–edge service systems. © 2014 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

MMA: Video Reconstruction for Spike Camera Based on Multiscale Temporal Modeling and Fine-Grained Attention

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1291-1295页

作者： Alim, Dilmurat Yang, Chen Qing, Laiyun Li, Guorong Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China

This paper presents a Multiscale Temporal Correlation Learning with the Mamba-Fused Attention Model (MMA), an efficient and effective method for reconstructing a video clip from a spike stream. Spike cameras offer unique advantages for capturing rapid scene changes with high temporal resolution. A spike stream contains sufficient information for multiple image reconstructions. However, existing methods generate only a single image at a time for a given spike stream, which results in excessive redundant computations between consecutive frames when aiming at restoring a video clip, thereby increasing computational costs significantly. The proposed MMA addresses such challenges by constructing a spike-to-video model, directly producing an image sequence at a time. Specifically, we propose a U-shaped Multiscale Temporal Correlation Learning (MTCL) to fuse the features at different temporal resolutions for clear video reconstruction. At each scale, we introduce a Fine-Grained Attention (FGA) module for fine-spatial context modeling within a patch and a Mamba module for integrating features across patches. Adopting a lightweight U-shaped structure and fine-grained feature extraction at each level, our method reconstructs high-quality image sequences quickly. The experimental results show that the proposed MMA surpasses current state-of-the-art methods in image quality, computation cost, and model size.

关键词： Feature extraction Streaming media Computational modeling Decoding Cameras Training Image quality Computer architecture Image sequences Spike cameras image reconstruction transformer Mamba Mamba

来源：评论

学校读者我要写书评

暂无评论

Supply-Demand risk assessment of urban flood resilience from the perspective of the ecosystem services: A case study in Nanjing, China

引用

ECOLOGICAL INDICATORS 2025年 173卷

作者： Zhang, Peng Xu, Xukan Yang, Wentong Li, Yiming Yao, Shengqi Hohai Univ Business Sch Nanjing 211100 Peoples R China Hohai Univ Inst Stat & Data Sci Nanjing 211100 Peoples R China Key Lab Ind Big Data Min & Knowledge Management Changzhou 213000 Peoples R China

Urban flooding has become a pressing challenge for many countries and regions. Meanwhile, ecosystem-based disaster risk reduction approaches have been recognized as a sustainable and effective strategy for managing flood risks. This study designed a conceptual framework for assessing the supply-demand risk of urban flood resilience (UFR) from the perspective of ecosystem services (ESs). Taking the city of Nanjing, China, as an example, the InVEST model and the multi-criteria comprehensive evaluation method were employed to quantify the supply of UFR provided by natural ecosystems and the demand for UFR from socio-economic systems. Additionally, based on UFR supply-demand evaluation indicators calculated for each subdistrict, the Self- Organizing Map (SOM) was used to cluster the subdistricts. Finally, UFR supply-demand matching was conducted on the subdistrict clusters, and different flood-risk levels were identified based on the supply-demand ratio. The results showed that high flood-risk subdistricts are mainly concentrated in central urban area, low flood-risk subdistricts are primarily in urban periphery, and subdistricts in urban-rural transitional zones exhibit medium flood risk. Statistical analysis revealed that this zonal pattern is closely related to land use types and the distribution of social resources. Therefore, this study provides a scientific basis for developing management strategies of urban flood prevention from the perspective of ESs.

关键词： Urban flood resilience Ecosystem services Self-Organizing Map Supply-demand matching Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Digitizing Highways:Unleashing Potential Through data Element Circulation for Safety,Cost Efficiency,and Environmental Impact Optimization

引用

Journal of Systems Science and Information 2025年第1期13卷 23-60页

作者： Yanyan JIA Wen LONG Yingjie TIAN School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Research Center on Fictitious Economy and Data Science Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China

As the era of large-scale highway maintenance arrives,the maintenance strategies have transitioned to a holistic approach that prioritizes safety,economic feasibility,and environmental *** research introduces a multi-objective optimization model for highway maintenance that incorporates the interplay of decision-maker preferences across three key objectives:Highway safety performance,maintenance engineering cost,and carbon *** study employs a large-sample data analysis on a subset of the Lianhuo Highway network,which includes 2,842 pavement *** approach mitigates the impact of outliers,ensuring a substantial data buffer that fortifies the model’s capacity for generalization and bolsters its *** findings reveal a Pareto-optimal relationship among the three scrutinized variables.A particularly noteworthy observation is the M-shaped trajectory of carbon emissions,which initially rise,then decline,and ultimately rebound,contingent upon the selected maintenance ***,an examination of the relationship between maintenance costs and safety performance discloses a trend of diminishing marginal returns,illustrating that the incremental gains in safety performance attenuate as maintenance investment escalates.

关键词： data element circulation highway maintenance multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Boost Tracking by Natural Language With Prompt-Guided Grounding

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 1088-1100页

作者： Li, Hengyou Liu, Xinyan Li, Guorong Wang, Shuhui Qing, Laiyun Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100045 Peoples R China

TNL (Tracking by Natural Language) aims to locate the target described by a natural language sentence in a video. Most existing TNL methods are typically composed of three modules: object grounding, object tracking, and switching module, and their performance is limited by the poor performance of the grounding and switching modules due to the complex backgrounds and inaccurate information stored in the memory. This paper presents a global-local framework to address these issues, which includes a prompt-guided grounding module, a trained local tracking module, and a memory-based switcher module. The prompt-guided grounding module uses noun prompts to guide the CLIP model in focusing more on target regions and aligning visual features semantically with linguistic features, avoiding being misled by distractors and background. The memory-based switch module stores historical information with higher-quality memory, allowing the model to make more accurate decisions based on reliable data, thus improving the overall performance. Experiments on TNL2K, LaSOT, and OTB-Lang demonstrate the effectiveness and generalizability of the proposed framework.

关键词： Target tracking Grounding Switches Visualization Feature extraction Computational modeling Adaptation models Location awareness Linguistics Memory management Vision-language tracking prompt learning inverse tracking

来源：评论

学校读者我要写书评

暂无评论

Subpart Suppression Network for Few-Shot Object Counting

Subpart Suppression Network for Few-Shot Object Counting

引用

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

作者： Liu, Lanxin Liu, Xinyan Li, Guorong School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China School of Computer Science and Technology Harbin Institute of Technology Weihai China

ISBN: (纸本)9798350368741

Few-shot object counting and detection aim to count objects along with their bounding boxes specified by exemplar bounding boxes. Current mainstream methods predict density maps by applying similarity between exemplar and image features to get counting results and detecting peak points from the density map as the positions of objects. However, the sub-parts of objects can also have high similarity to the exemplars, harming the counting and detection performance. To address these issues, we propose a two-stage Subpart Suppression Network (SSN), consisting of a Subpart Suppression Density map Predictor (SSDP), which enforces the model focus on whole objects rather than subparts, and a SAM-based Detector and Verifier, which refines the final prediction by a clustering method. Extensive experiments on two popular datasets show an advantage in performance over the state-of-the-art methods and prove the components' effectiveness. © 2025 IEEE.

关键词： Counting Detection Few-Shot Localization

来源：评论

学校读者我要写书评

暂无评论

XAI-driven assessment of urban circular carbon economy: Using China's pilot cities as a case study

引用

URBAN CLIMATE 2025年 61卷

作者： Wang, Ning Zhai, Hao Bai, Yubing Fan, Yu Beijing Informat Sci & Technol Univ Beijing 102206 Peoples R China Beijing Key Lab Green Dev Decis Based Big Data Beijing 102206 Peoples R China Beijing Knowledge Management Res Ctr Beijing 100192 Peoples R China

The confluence of circular economy and carbon emission mitigation strategies has catalyzed the emergence of a concept called the Circular Carbon Economy (CCE). This study introduces a novel CCE evaluation framework targeting urban areas and employs Explainable Artificial Intelligence (XAI) to bolster transparency and interpretability. Through the application of big data mining techniques, key indicators were extracted from literature and policy documents to construct a multi-dimensional CCE evaluation system. This system was integrated with the Explainable Boosting Machine (EBM) model-a key XAI technique-to resolve the precision-interpretability trade-off prevalent in traditional models. The EBM-based framework achieves black-box-level accuracy while providing transparent decision pathways through feature importance quantification. Empirical validation with China's Circular Economy pilot cities demonstrates its applicability, offering a transferable paradigm for global urban CCE assessments. Our findings show that industrial solid waste utilization and the promotion of green buildings are the most critical drivers for advancing CCE in urban areas. The city rankings generated by the EBM model bolster the scientific validity and reliability of our framework. Moreover, the study uncovers significant regional disparities, with cities located in eastern and central China generally exhibiting higher levels of CCE development compared to their western and northeastern counterparts. Based on these insights, we propose three key recommendations-targeted development strategies, differentiated evaluation frameworks, and balanced regional development-to lay the theoretical groundwork and offer practical guidance for urban-level CCE development.

关键词： Circular carbon economy (CCE) Explainable artificial intelligence (XAI) CCE evaluation framework

来源：评论

学校读者我要写书评

暂无评论

Robust sparse orthogonal basis clustering for unsupervised feature selection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 274卷

作者： Miao, Jianyu Zhao, Jingjing Yang, Tiejun Tian, Yingjie Shi, Yong Xu, Mingliang Henan Univ Technol Sch Artificial Intelligence & Big Data Zhengzhou 450001 Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou 450001 Peoples R China

Unsupervised Feature Selection (UFS), which identifies the optimal-related feature subset from the original feature set to lower the dimensionality of data without label information, has had a high profile in recent years. Given the absence of label information, the existing UFS approaches usually utilize graph and manifold learning techniques to retain the intrinsic structure of the data. The inclusion of irrelevant and redundant features and noise, would inevitably lower the quality of the structure. For this purpose, in this paper, we come up with Robust Sparse Orthogonal Basis Clustering (RSOBC), a novel method for UFS that integrates feature selection process with clustering task into a unified framework. Instead of explicitly utilizing the pre-computed local information, such a strategy focuses on exploring the inherent clustering structures of data. RSOBC leverages the log-based function as the loss to lessen the effect of noise and outliers, thereby enhancing its robustness. To select the more useful and discriminative features, the l2,1 norm is employed as the sparse regularization to encourage sparsity of the projection matrix. Meanwhile, we adopt the low redundancy regularization to make the weights of the correlated features small. In this way, the correlated features cannot be selected simultaneously. Consequently, the projection matrix, centroid matrix and cluster label matrix are learned simultaneously, such that the intrinsic structure is constructed in amore accurate way. The resulting optimization can be readily tackled by multi-block Alternating Direction Method of Multipliers (ADMM) based algorithm. Comprehensive experiments have been carried out on nine diverse real-world datasets. The results demonstrate that RSOBC surpasses many state-of-the-art UFS approaches, which indicates its effectiveness and superiority.

关键词： Unsupervised feature selection Robust loss function Sparse regularization Low redundancy

来源：评论

学校读者我要写书评

暂无评论

Class-view graph knowledge distillation: A new idea for learning MLPs on graphs

引用

NEUROCOMPUTING 2025年 637卷

作者： Tian, Yingjie Xu, Shaokai Li, Muyang Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Graph Neural Networks (GNNs), while effective for processing non-Euclidean structured data, suffer from computationally intensive neighbor fetching, which hinders their deployment in low-latency applications. Cross-architecture graph knowledge distillation (KD), which trains high-performance Multi-layer Perceptrons (MLPs) to emulate teacher GNNs, offers a promising solution. However, existing GNN-MLP distillation methods rely on the sample-view KD paradigm, where student models directly mimic the teacher's parameter space. Given the fundamentally different architectures and parameter spaces of GNNs and MLPs, this direct mimicry approach limits effective knowledge transfer. Inspired by the inherent properties of MLPs, we propose a novel class-view KD paradigm for GNN-MLP distillation. Unlike sample-view KD, our method guides student MLPs to generate more discriminative parameter configurations within their own parameter space while preserving the similarity of prediction distributions with the teacher, rather than directly imitating the teacher's parameter configurations. Extensive experiments on public benchmark datasets demonstrate that class-view KD outperforms sample-view KD across various evaluation metrics and can be seamlessly integrated into existing GNN-MLP distillation methods to improve performance without additional computational cost. The code is available at https://***/xsk160/Class-View-Graph-KD.

关键词： Graph knowledge distillation Cross-architecture Class-view

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：