检索结果-内蒙古大学图书馆

Meta-Learning-Based Semi-Supervised Change Detection in Remote Sensing Images

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Tang, Yi Zhang, Liyi Zhang, Wuxia Jiang, Zuo Yunnan Minzu Univ Sch Math & Comp Sci Kunming 650504 Peoples R China Xian Univ Posts & Telecommun Sch Comp Sci & Technol Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Peoples R China

Semi-supervised change detection methods with consistency regularization, which overcome the lack of labeled samples by using unlabeled samples and enforcing consistent predictions under weak perturbations. However, current consistency regularization methods lack randomness in their perturbation settings and treat all samples uniformly, limiting the model's ability to leverage sample diversity to improve generalization. In contrast, meta-learning methods shift focus from individual samples to learning patterns across similar tasks, thereby enhancing information efficiency and model generalization. Inspired by these principles, we propose a meta-learning-based semi-supervised change detection (MLSCD) method for remote sensing images, which aims to explore and leverage meta-learning methods to enhance the generalization capabilities of consistency regularization-based semi-supervised change detection. First, we set the degree of weak perturbation and the combination of different types of perturbations as random parameters to generate diverse and randomized weak perturbations. Second, we redefine consistency regularization-based semi-supervised change detection from a meta-learning perspective, which learns patterns from diverse perturbation tasks to improve sample utilization efficiency, thereby enhancing the model's generalization capability. Third, we balance accuracy and efficiency by using AdamW for cross-task updates in the outer loop and stochastic gradient descent (SGD) for single-task optimization in the inner loop, which experimental results demonstrate is an ideal method for applying meta-learning to remote sensing change detection. Finally, the superiority of the proposed method is validated on two datasets. The extensive experimental results demonstrate the superior performance of the proposed method compared to state-of-the-art methods.

关键词： Perturbation methods Metalearning Remote sensing Feature extraction Adaptation models data models Training Robustness Optimization Noise Change detection meta-learning semi-supervised learning task diversity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Barrage Jamming Against SAR Based on Prior Information and Scene Segmentation

引用

REMOTE SENSING 2025年第7期17卷 1303-1303页

作者： Guo, Zhengwei Wang, Longyuan Liu, Zhenchang Fu, Zewen Li, Ning Zhang, Xuebo Henan Kaifeng Coll Sci Technol & Commun Kaifeng 475000 Peoples R China Henan Engn Res Ctr AI Technol Converged Media Kaifeng 471699 Peoples R China Henan Univ Henan Engn Res Ctr Intelligent Technol & Applicat Kaifeng 475004 Peoples R China Henan Univ Henan Key Lab Big Data Anal & Proc Kaifeng 475004 Peoples R China Henan Univ Coll Comp & Informat Engn Kaifeng 475004 Peoples R China Northwest Normal Univ Coll Phys & Elect Engn Lanzhou 730070 Peoples R China

Due to the advantages of easy implementation and fine jamming effect, barrage jamming against synthetic aperture radar (SAR) has received extensive attention in the field of electronic countermeasures. However, most methods of barrage jamming still have limitations, such as uncontrollable jamming position and coverage and high-power requirements. To address these issues, an improved barrage jamming method is proposed in this paper. The proposed method fully combines the prior information of the region of interest (ROI), and the precise jamming with controllable position, coverage, and power is realized. For the proposed method, the ROI is firstly divided into several sub-scenes according to the obtained prior information, and the signal is intercepted. Then the frequency response function of the jammer for each sub-scene is generated. The frequency response function of the jammer, which consists of position modulation function and jamming coverage function, is decomposed into slow-time-dependent parts and slow-time-independent parts. The slow-time-independent parts are generated offline in advance, and the real-time performance of the proposed method is guaranteed through this way. Finally, the intercepted signal is modulated by the frequency response function to generate the two-dimensional controllable jamming effect. Theoretical analysis and simulation results show that the proposed method can produce jamming effects with controllable position and coverage, and the utilization efficiency of jamming power is improved.

关键词： barrage jamming frequency response function synthetic aperture radar (SAR) space-borne SAR prior information scene segmentation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection With Multi-Scale Granular Balls

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第3期37卷 1182-1197页

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Nantong Univ Sch Artificial Intelligence & Comp Sci Nantong 226019 Peoples R China City Univ Macau Fac Data Sci Macau 999078 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada Polish Acad Sci Syst Res Inst PL-00901 Warsaw Poland Istinye Univ Res Ctr Performance & Prod Anal TR-34010 Istanbul Turkiye

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index.

关键词： Anomaly detection Rough sets Information systems Entropy Accuracy Support vector machines Indexes Weight measurement Video surveillance Urban areas Outlier detection fuzzy rough sets fuzzy granule density multi-scale granular balls three-way decision

来源：评论

学校读者我要写书评

暂无评论

Granule Margin-Based Feature Selection in Weighted Neighborhood Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2025年第5期55卷 2151-2164页

作者： Gao, Can Zhou, Jie Wang, Xizhao Pedrycz, Witold Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Guangdong Peoples R China Silesian Tech Univ Dept Measurement & Control Syst PL-44100 Gliwice Poland Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada Istinye Univ Res Ctr Performance & Prod Anal TR-34010 Istanbul Turkiye

Neighborhood rough sets are an effective model for handling numerical and categorical data entangled with vagueness, imprecision, or uncertainty. However, existing neighborhood rough set models and their feature selection methods treat each sample equally, whereas different types of samples inherently play different roles in constructing neighborhood granules and evaluating the goodness of features. In this study, the sample weight information is first introduced into neighborhood rough sets, and a novel weighted neighborhood rough set model is consequently constructed. Then, considering the lack of sample weight information in practical data, a margin-based weight optimization function is designed, based on which a gradient descent algorithm is provided to adaptively learn sample weights through maximizing sample margins. Finally, an average granule margin measure is put forward for feature selection, and a forward-adding heuristic algorithm is developed to generate an optimal feature subset. The proposed method constructs the weighted neighborhood rough sets using sample weights for the first time and is able to yield compact feature subsets with a large margin. Extensive experiments and statistical analysis on UCI datasets show that the proposed method achieves highly competitive performance in terms of feature reduction rate and classification accuracy when compared with other state-of-the-art methods.

关键词： Rough sets Feature extraction Measurement Numerical models Heuristic algorithms data models Adaptation models Uncertainty Optimization methods Measurement uncertainty Average granule margin (AGM) feature selection gradient optimization neighborhood rough sets sample weighting

来源：评论

学校读者我要写书评

暂无评论

LOGLformer: Integrating local and global characteristics for depression scale estimation from facial expressions

引用

REVIEW OF SCIENTIFIC INSTRUMENTS 2025年第3期96卷 035117页

作者： Cao, Cui He, Lang Weinan Normal Univ Sch Arts Xian Shaanxi Peoples R China Xian Univ Posts & Telecommun Sch Comp Sci & Technol 618 Changan West St Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr 618 Changan West St Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Xian Key Lab Big Data & Intelligent Comp 618 Changan West St Xian 710121 Shaanxi Peoples R China

According to a publication by the World Health Organization, depression is projected to emerge as the leading mental health issue. In the domain of affective computing, deep learning techniques are frequently employed to represent facial dynamics using both local and global perspectives for the purpose of automatic depression detection (ADD). Yet, current models overlook the crucial interplay between local and global dynamics in discerning the significant features essential for ADD. Addressing this oversight, a novel hybrid computational architecture, named LOGLFormer, has been introduced. This architecture integrates CNN-derived local attributes and transformer-sourced global patterns tailored for ADD. Within LOGLFormer, the design philosophies of ResNet and ViT inspire the CNN and transformer branches, respectively. The synergy of these branches encompasses local convolutional mechanisms, self-attention strategies, and multilayer perceptron entities. Furthermore, the intricacies arising from disparities in CNN and transformer feature sets are reconciled through the specially devised feature alignment module. Rigorous comparative analysis underscores the distinctive efficacy of the LOGLFormer in recognizing depression, notably outperforming several state-of-the-art techniques on two dedicated depression databases: AVEC2013 and AVEC2014. Code will be available at https://***/helang818/LOGLFormer.

关键词： Philosophical aspects

来源：评论

学校读者我要写书评

暂无评论

NBIGAN: Automatic nasopharyngeal white light and narrow band imaging transformation based on feature aggregation and perceptual generative adversarial networks

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 271卷

作者： Pan, Xiaoying Chen, Han Zhang, Zizheng Wen, Wulin Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Shaanxi Peoples R China First Peoples Hosp Yinchuan Yinchuan 750003 Ningxia Peoples R China

Nasopharyngeal Narrow Band Imaging (NBI) data are very important for the clinical diagnosis and treatment of nasopharyngeal early cancer. However, acquiring NBI data heavily relies on optical imaging equipment, which is not widely available. Existing models fail to maintain the structural integrity of white light data while producing high-contrast, clear NBI-style images from white light images. To address these issues, this paper proposes an automatic conversion method, Narrow Band Imaging Generative Adversarial network (NBIGAN), suitable for unpaired white light and narrow-band light images. NBIGAN incorporates a global attention holistic perception module (HPM), at the bottleneck of the generator, enabling global information perception and adjustment of long-range dependencies. In the encoder part, a multi-scale feature aggregation module (MSFA), is introduced to ensure the fusion of contextual information while preserving feature positions. Moreover, NBIGAN constrains and enhances the quality of generated NBI images from the perspectives of texture fidelity and light distribution. Experimental results demonstrate outstanding performance of NBIGAN in overall structure, NBI-style presentation, lighting differences, and highlighting superficial microvascular textures.

关键词： Narrow-Band Imaging StillGAN Nasopharyngeal medical image processing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A hierarchical and interlamination graph self-attention mechanism-based knowledge graph reasoning architecture

引用

INFORMATION SCIENCES 2025年 686卷

作者： Wu, Yuejia Zhou, Jian-tao Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Minist Educ Engn Res Ctr Ecol Big Data Hohhot Peoples R China Inner Mongolia Engn Lab Cloud Comp & Serv Softwar Hohhot Peoples R China Inner Mongolia Key Lab Social Comp & Data Proc Hohhot Peoples R China Inner Mongolia Key Lab Discipline Inspect & Super Hohhot Peoples R China Inner Mongolia Engn Lab Big Data Anal Technol Hohhot Peoples R China

Knowledge Graph (KG) is an essential research field in graph theory, but its inherent incompleteness and sparsity influence its performance in several fields. Knowledge Graph Reasoning (KGR) aims to ameliorate those problems by mining new knowledge from subsistent knowledge. As one of the downstream tasks of KGR, link prediction is of great significance for improving the quality of KG. Recently, the Graph Neural network (GNN)-based method became the most effective way to achieve the link prediction task. However, it still suffers from problems such as incomplete neighbor and relation-level information aggregation and unstable learning of the entity's features. To improve those issues, a Hierarchical and Interlamination Graph Self-attention Mechanism- based (HIGSM) plug-and-play architecture is proposed for KGR in this paper. It is composed of three-level layers: feature extractor, encoder, and decoder. The feature extractor makes our architecture more effective and stable for the retrieval of new features. The encoder is equipped with a two-stage encoding mechanism accompanied by two mixture-of-expert strategies, which enables our architecture to capture more practical reasoning information to improve prediction accuracy and generalization of the model. The decoder can use existing KGR models and compute the scores of triples in KG. The extensive experimental results and ablation studies on four KGs unambiguously demonstrate the state-of-the-art prediction performance of the proposed HIGSM architecture compared to current GNN-based methods.

关键词： Knowledge graph reasoning Graph self-attention mechanism Variational autoencoder Mixture-of-expert Link prediction

来源：评论

学校读者我要写书评

暂无评论

HardVD: High-capacity cross-modal adversarial reprogramming for data-efficient vulnerability detection

引用

INFORMATION SCIENCES 2025年 686卷

作者： Tian, Zhenzhou Li, Haojiang Sun, Hanlin Chen, Yanping Chen, Lingwei Xian Univ Posts & Telecommun Sch Comp Sci & Technol West Changan Ave Xian 710121 Shaanxi Peoples R China Shaanxi Key Lab Network Data Anal & Intelligent Pr West Changan Ave Xian 710121 Shaanxi Peoples R China Wright State Univ Dept Comp Sci & Engn 3640 Colonel Glenn Hwy Dayton OH 45435 USA

The substantial proliferation of software vulnerabilities poses a persistent threat to system security, driving increased interest in applying deep learning (DL) for vulnerability detection. However, DL-based detectors often operate with a fixed number of input tokens, leading to semantic loss over large code snippets. Additionally, developing these detectors demands substantial labeled data and training time. To address these limitations, this paper proposes HardVD, which explores High-capacity cross-modal adversarial reprogramming for data-efficient Vulnerability Detection. HardVD devises a high-capacity semantic extractor to capture salient features per line of code, which are then arranged as patches to form an image representing the target function. These images are processed using convolutional filters as universal perturbations and non-parametric label remapping to adapt a pretrained Vision Transformer (ViT) for vulnerability detection, updating only the limited parameters of the perturbation filters during training. Extensive experiments demonstrate that HardVD outperforms DL-based baselines in terms of detection effectiveness, data-limited performance, and computational overhead. The ablation study also confirms the essential role of our high-capacity semantic extractor, without which an averaged relative decrease of 5.87% and 7.98% in accuracy and F1 score is observed, respectively.

关键词： Vulnerability detection Cross-modal adversarial reprogramming High capacity data scarcity

来源：评论

学校读者我要写书评

暂无评论

Skeleton-based action recognition through dual-granularity feature fusion with self-adapting graph convolution and multi-scale temporal convolution

引用

NEUROCOMPUTING 2025年 639卷

作者： Chen, Hao Shen, YiHao Zhang, YuanXiang Pan, XiaoYing Yang, Qing Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Shaanxi Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Shaanxi Peoples R China Xian Phys Educ Univ Sch Sport & Hlth Sci Xian 710068 Shaanxi Peoples R China

3-D skeleton sequences have been widely applied in human recognition tasks due to their ability of filtering out the interferences caused by multiple uncertainties such as background noise and illumination changing. Simultaneously, the Graph Convolutional networks (GCNs) were developed to perform feature learning from the skeleton sequences, thereby providing a pivotal method for human action recognition. However, in related researches, the complexity and computation of such models need to be greatly increased to obtain a small accuracy improvement. To deploy such models on edge devices or mobile devices, it is necessary to reduce the complexity and computational overhead of GCNs without significantly affecting their performance. This study developed a novel GCN lightweight method for human action recognition. Firstly, we proposed to extract and fuse the meta-action features and local joint motion features from 3-D skeleton sequences, replacing the multi-stream architecture or multiple convolutional layers, for mining out the key motion features, which helps to significantly reduce the number of network parameters and overall computational load. Next, we designed the MTGCN network to perform action classification with a self-adaption graph convolution module for capturing deeper dependencies between joints during movement, and an attention mechanism based multi-scale temporal convolution module for handling the actions with different limb movement patterns over multiple time spans. Comparative experiments with 11 typical methods on two datasets, NTU RGB D+60 and NTU RGB D+120, showed the proposed method, while nearing the recognition accuracy of existing SOTA methods, required only about one-twentieth of the number of parameters and computational cost.

关键词： 3-D skeleton sequences Human action recognition Dual-granularity features Graph convolution networks Multi-scale temporal convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-scale contrastive learning method for PolSAR image classification

引用

JOURNAL OF APPLIED REMOTE SENSING 2024年第1期18卷

作者： Hua, Wenqiang Wang, Chen Sun, Nan Liu, Lin Xian Univ Posts & Telecommun Sch Comp Sci & Technol Shaanxi Key Lab Network Data Anal & Intelligent P Xian Key Lab Big Data & Intelligent Comp Xian Peoples R China

. Although deep learning-based methods have made remarkable achievements in polarimetric synthetic aperture radar (PolSAR) image classification, these methods require a large number of labeled samples. However, for PolSAR image classification, it is difficult to obtain a large number of labeled samples, which requires extensive human labor and material resources. Therefore, a new PolSAR image classification method based on multi-scale contrastive learning is proposed, which can achieve good classification results with only a small number of labeled samples. During the pre-training process, we propose a multi-scale contrastive learning network model that uses the characteristics of the data itself to train the network by contrastive training. In addition, to capture richer feature information, a multi-scale network structure is introduced. In the training process, considering the diversity and complexity of PolSAR images, we design a hybrid loss function combining the supervised and unsupervised information to achieve better classification performance with limited labeled samples. The experimental results on three real PolSAR datasets have demonstrated that the proposed method outperforms other comparison methods, even with limited labeled samples.

关键词： contrastive learning polarimetric synthetic aperture radar image terrain classification self-supervised 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：