检索结果-内蒙古大学图书馆

Class-Balanced Sampling and Discriminative Stylization for Domain Generalization Semantic Segmentation

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第2期26卷 2596-2608页

作者： Liao, Muxin Tian, Shishun Wei, Binbin Zhang, Yuhang Zou, Wenbin Li, Xia Jiangxi Agr Univ Sch Comp Sci & Engn Nanchang 330045 Peoples R China Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Key Lab Adv Machine Learning & Applicat Guangdong Key Lab Intelligent Informat Proc Inst Artificial Intelligence & Adv CommunColl Ele Shenzhen 518060 Peoples R China

Existing domain generalization semantic segmentation (DGSS) methods have achieved remarkable performance on unseen domains by generating stylized images to increase the diversity of training data. However, since the training data is usually class-imbalanced, uniform style randomization is unable to generate diverse minority classes. This means that models may overfit to the minority classes, resulting in suboptimal performance on the minority classes. In addition, the image-level style randomization may also corrupt the class-discriminative regions of objects, leading to a loss of the class-discriminative representation. To address these issues, a novel class-balanced sampling and discriminative stylization (CSDS) approach is proposed for DGSS. Specifically, first, a pixel-level class-balanced sampling (PCS) strategy is proposed to adaptively sample patches of the minority classes from the source domain images and paste the sampled patches on the input images. Unlike existing class sampling strategies that fix the minority classes, the PCS strategy dynamically determines the minority classes by estimating the class distribution after each sampling. Then, a class-discriminative style randomization (CSR) strategy is proposed to increase the style diversity of the sampled patches while preserving the class-discriminative regions. Finally, since the pasting positions of the sampled patches are uncertain, which may confuse the semantic relations between the classes, a semantic consistency constraint is proposed to ensure the learning of reliable semantic relations. Extensive experiments demonstrate that the proposed approach achieves superior performance compared to existing DGSS methods on multiple benchmarks. The source code has been released on https://***/seabearlmx/CSDS.

关键词： Semantic segmentation Semantics Intelligent transportation systems Training data Training Benchmark testing Automobiles Adaptation models Tires Motorcycles Domain generalization semantic segmentation adaptively class-balanced sampling class-discriminative stylization

来源：评论

学校读者我要写书评

暂无评论

A global reweighting approach for cross-domain semantic segmentation

引用

SIGNAL procESSING-IMAGE communICATION 2025年 130卷

作者： Zhang, Yuhang Tian, Shishun Liao, Muxin Hua, Guoguang Zou, Wenbin Xu, Chen Shenzhen Univ Shenzhen Key Lab Adv Machine Learning & Applicat Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Inst Artificial Intelligence & Adv Commun Shenzhen 518060 Peoples R China Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Peoples R China Shenzhen Univ Coll Math & Stat Shenzhen 518060 Peoples R China

Unsupervised domain adaptation semantic segmentation attracts much research attention due to the expensive pixel-level annotation cost. Since the adaptation difficulty of samples is different, the weight of samples should be set independently, which is called reweighting. However, existing reweighting methods only calculate local reweighting information from predicted results or context information in batch images of two domains, which may lead to over-alignment or under-alignment problems. To handle this issue, we propose a global reweighting approach. Specifically, we first define the target centroid distance, which describes the distance between the source batch data and the target centroid. Then, we employ a Fr & eacute;chet Inception Distance metric to evaluate the domain divergence and embed it into the target centroid distance. Finally, a global reweighting strategy is proposed to enhance the knowledge transferability in the source domain supervision. Extensive experiments demonstrate that our approach achieves competitive performance and helps to improve performance in other methods.

关键词： Unsupervised domain adaptation Semantic segmentation Reweighting Domain divergence

来源：评论

学校读者我要写书评

暂无评论

A progressive segmentation network for navigable areas with semantic-spatial information flow

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 261卷

作者： Li, Wei Liao, Muxin Zou, Wenbin Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Shenzhen Key Lab Adv Machine Learning & Applicat Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Guangdong Peoples R China

Segmentation of safe navigable areas is a crucial technology for scene parsing in autopilot systems. However, existing segmentation methods often fail to adequately exploit the complementary relationships between multiscale features in complex wild environments, resulting in insufficient information fusion. In pursuit of a resolution, a Progressive Segmentation Network (PSNet) is proposed for navigable areas segmentation, which builds a semantic-spatial information flow branch to dynamically exploit the complementary relationships between multiscale features for progressive guided learning. Specifically, PSNet consists of four essential modules, including the Local Capturer and Global dependence Builder (LCGB), Multi-Directional Pooling Module (MDPM), Fusion-wise Module (FWM), and Spatial Weight Aggregation Module (SWAM). To facilitate efficient information dissemination, the LCGB was utilized to capture dense spatial information, and the MDPM was proposed to extract global geometric information of obstacles. These pieces of information serve as prior knowledge to guide learning. Additionally, we propose the FWM based on attention fusion unit (AFU) and contribution weights unit (CWU) to construct the complementary relationships between multiscale features and obtain rich multiscale fusion information. SWAM is proposed to enhance the significant spatial features from FWM and achieve impressive segmentation results. Extensive experimental results on the wild datasets demonstrate that PSNet outperforms state-of-the-art methods in recognizing safe navigable areas. The code for PSNet will be available at https://***/lv881314/PSNet.

关键词： Navigable areas Deep neural networks Auxiliary information Semantic-spatial information flow Spatial weight aggregation

来源：评论

学校读者我要写书评

暂无评论

Global-local prototype-based few-shot learning for cross-domain hyperspectral image classification

引用

KNOWLEDGE-BASED SYSTEMS 2025年 314卷

作者： Tang, Haojin Wu, Yuelin Li, Hongyi Tang, Dong Yang, Xiaofei Xie, Weixin Guangzhou Univ Sch Elect & Commun Engn Guangzhou 511370 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

Because cross-domain information can help in tackling the small-sample-size challenge, cross-domain hyper- spectral image (HSI) classification has become a hot issue in recent years. Few-shot learning (FSL) has been recognized as an effective solution for cross-domain HSI classification. In particular, the prototype-based FSL method, which aims to train a generalized feature metric space by performing feature matching between prototypes and query samples, is the most commonly used FSL method for cross-domain HSI classification. However, existing prototype-based FSL methods mainly use the global semantic information of the HSI pixel neighborhood to establish the prototype-based feature metric space. This ignores the local semantic information and fails to exploit the global-local semantic relationship of the HSI pixel neighborhood. To address this problem, a novel global-local prototype-based FSL (GLP-FSL) is proposed for cross-domain HSI classification in this study. First, we propose a multiview spatial-spectral feature extraction module to capture both global-view and local-view spatial-spectral features across domains. Second, we present a global-local spatial-spectral feature-matching module to better achieve prototype-based spatial-spectral feature matching by exploiting the global-local semantic relationship. Moreover, a spatial-spectral domain-adaptation strategy based on global-local knowledge distillation is designed for boosting the universal applicability of the feature metric space. Finally, the proposed GLP-FSL is evaluated on five public HSI datasets, and the extensive experimental results indicate that the proposed GLP-FSL considerably outperforms other state-of-the-art FSL methods.

关键词： Hyperspectral image classification Cross-domain Prototype-based few-shot learning Global-local spatial-spectral feature Knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Global-Local Attention-Aware Zero-Shot Learning for Industrial Fault Diagnosis

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Tang, Haojin Jing, Wei Tang, Dong Yang, Zhao Yang, Xiaofei Xie, Weixin GuangZhou Univ Sch Elect & Commun Engn Guangzhou 511370 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

The industrial fault diagnosis is recognized as a significant technology in industrial systems. Since the breakdown events rarely happen, the scarcity of labeled fault data poses a great challenge for industrial fault diagnosis. Zero-shot learning (ZSL) has emerged as a promising approach in industrial fault diagnosis, enabling models to classify previously unseen fault data without using labeled samples. However, existing ZSL methods primarily focus on exploiting global-level fault features, but fail to capture local-level fault features that characterize the topological relationships between neighboring data points, leading to a degradation in their generalization performance. To address these issues, we propose a global-local attention-aware ZSL (GLA-ZSL) method for industrial fault diagnosis. First, we design a global prior refinement module (GPRM) using 2D-CNN to capture the global-level fault features. Second, we present a local feature enhancement module (LFEM) based on the channel attention and 1D-CNN, which utilizes the extracted global-level fault features as input to deeply extract local-level fault features. Furthermore, a meta-learning strategy based on the prototype distance metric for ZSL is proposed to learn more discriminative global-local fault features and improve the generalization performance of the model. Finally, the proposed GLA-ZSL is evaluated on the Tennessee Eastman process (TEP) dataset, the Case Western Reserve University (CWRU) dataset, and the Jiangnan University (JNU) bearing dataset. The experimental results demonstrate that the proposed GLA-ZSL method significantly outperforms other representative ZSL methods.

关键词： Attention mechanism global-local fault fea- tures industrial fault diagnosis meta-learning meta-learning zero-shot learn- ing (ZSL) zero-shot learn- ing (ZSL)

来源：评论

学校读者我要写书评

暂无评论

Dual Residual-Guided Interactive Learning for the Quality Assessment of Enhanced Images

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 1637-1651页

作者： Tian, Shishun Zeng, Tiantian Zhang, Zhengyu Zou, Wenbin Li, Xia Shenzhen Univ Coll Elect & Informat Engn Guangdong Prov Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Guangzhou Univ Sch Elect & Commun Engn Guangzhou 511370 Peoples R China

Image enhancement algorithms can facilitate computer vision tasks in real applications. However, various distortions may also be introduced by image enhancement algorithms. Therefore, the image quality assessment (IQA) plays a crucial role in accurately evaluating enhanced images to provide dependable feedback. Current enhanced IQA methods are mainly designed for single specific scenarios, resulting in limited performance in other scenarios. Besides, no-reference methods predict quality utilizing enhanced images alone, which ignores the existing degraded images that contain valuable information, are not reliable enough. In this work, we propose a degraded-reference image quality assessment method based on dual residual-guided interactive learning (DRGQA) for the enhanced images in multiple scenarios. Specifically, a global and local feature collaboration module (GLCM) is proposed to imitate the perception of observers to capture comprehensive quality-aware features by using convolutional neural networks (CNN) and Transformers in an interactive manner. Then, we investigate the structure damage and color shift distortions that commonly occur in the enhanced images and propose a dual residual-guided module (DRGM) to make the model concentrate on the distorted regions that are sensitive to human visual system (HVS). Furthermore, a distortion-aware feature enhancement module (DEM) is proposed to improve the representation abilities of features in deeper networks. Extensive experimental results demonstrate that our proposed DRGQA achieves superior performance with lower computational complexity compared to the state-of-the-art IQA methods.

关键词： Degraded reference image quality assessment enhanced image enhanced image dual residual-guided dual residual-guided interactive learning interactive learning interactive learning

来源：评论

学校读者我要写书评

暂无评论

A terrain segmentation network for navigable areas with global strip reliability evaluation and dynamic fusion

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 265卷

Accurate segmentation of safe navigable areas is crucial for scene parsing in autonomous driving systems. However, existing segmentation methods often fail to fully leverage the complementary nature of multiscale features in complex environments, resulting in inadequate information extraction. To overcome this limitation, a Terrain Segmentation Network (TSNet) is proposed for navigable area segmentation, which introduces reliable global semantic information as fusion guide while dynamically exploiting the complementary relationships between multiscale features for progressively guided fusion. Specifically, TSNet is composed of the Global Strip Reliability Evaluation Module (GSREM) and the Dynamic Fusion Module (DFM). The GSREM, which includes the Global Strip Unit (GSU) and the Reliability-Evaluation Unit (REU), is designed to capture the global geometric information of obstacles with long-range contextual characteristics. The information from GSREM serves as prior knowledge to guide the feature fusion. Additionally, we propose the DFM, comprising the Attention Fusion Unit (AFU) and the Contribution Distribution Unit (CDU), to explore the complementary relationships among multiscale feature interactions and to obtain comprehensive scene information. Extensive experiments on diverse wild datasets demonstrate that TSNet outperforms the state-of-the-art methods in accurately identifying navigable areas. The code for TSNet will be available at https://***/lv881314/ 2TSNet.

关键词： Terrain segmentation Navigable areas Deep neural networks Global strip reliability evaluation Dynamic fusion

来源：评论

学校读者我要写书评

暂无评论

A Novel Wireless Vehicle Velocity Measurement Method Based on Machine Learning

引用

IEEE communICATIONS LETTERS 2025年第1期29卷 1-5页

作者： Liu, Yuxuan Zhang, Chiya He, Chunlong Harbin Inst Technol Sch Elect & Informat Engn Shenzhen 518055 Peoples R China Peng Cheng Lab PCL Shenzhen 518055 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 211189 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

High-precision vehicle velocity measurement methods typically require additional context, such as the rough location of the target vehicle. In the Internet of Vehicles domain, it is possible to achieve real-time vehicle velocity measurement based on the characteristics of wireless communication signals without any extra context. In this letter, we first propose a velocity measurement algorithm utilizing a convolutional neural network (CNN) with the differential constellation diagram of the wireless communication signal as input. We also develop an acceleration algorithm based on gated recurrent units (GRUs) that achieves higher accuracy than the CNN-based algorithm under high signal-to-noise ratio conditions. Subsequently, we propose a hierarchical model that can attain the highest accuracy, albeit with increased complexity. Finally, we analyze the theoretical upper bounds of accuracy for both the CNN-based and GRU-based algorithms. The performance of proposed algorithms is validated through simulations. Compared to signal based measurement methods, the proposed method has higher accuracy and has no requirements on synchronization. Moreover, the complexity of the GRU-based algorithm is lower.

关键词： Estimation Velocity measurement Constellation diagram Phase shift keying Wireless communication Convolutional neural networks Convolution IoV vehicle velocity measurement wireless communication CNN GRU

来源：评论

学校读者我要写书评

暂无评论

An improved random projection-type algorithm for solving multiple-sets split feasibility problems with application to medical radiotherapy

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2025年 463卷

作者： Chao, Wen-Jing Xia, Fu-Quan Tu, Kai Lu, Jian Sichuan Normal Univ Sch Math Sci Chengdu 610066 Peoples R China Shenzhen Univ Sch Math Sci Shenzhen 518000 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Sch Math Sci Shenzhen Key Lab Adv Machine Learning & Applicat Shenzhen 518000 Peoples R China Pazhou Lab Guangzhou 510000 Peoples R China

In this paper, we propose a simple variant of random projection-type algorithm for solving multiple-sets split feasibility problems. We employ random projection and self-adaptive step size techniques to do randomly chosen projections, which avoids computing all single constraint set projections at each iteration and the largest eigenvalue (spectral radius) of matrix. We prove the convergence theorem and sublinear convergence rate of the proposed algorithm, provided that the spectral radius of matrix is unknown or hard to compute. Furthermore, if this term is known, the linear convergence rate can be obtained. Numerical experiments are reported to illustrate the effectiveness of the proposed algorithm.

关键词： Random projection Self-adaptive step size Multiple-sets split feasibility problem Convergence rate analysis

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Symmetric Non-Negative Matrix Factorization With Low-Rank Tensor Representation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1534-1547页

作者： Jia, Yuheng Li, Jia-Nan Wu, Wenhui Wang, Ran Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Southeast Univ Key Lab New Generat Artificial Intelligence Techno Minist Educ Nanjing 211189 Peoples R China Shenzhen Univ Coll Elect & Informat Engn Shenzhen 518060 Peoples R China Shenzhen Univ Sch Math Sci Guangdong Prov Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Key Lab Adv Machine Learning & Applicat Shenzhen 518060 Peoples R China

Semi-supervised symmetric non-negative matrix factorization (SNMF) utilizes the available supervisory information (usually in the form of pairwise constraints) to improve the clustering ability of SNMF. The previous methods introduce the pairwise constraints from the local perspective, i.e., they either directly refine the similarity matrix element-wisely or restrain the distance of the decomposed vectors in pairs according to the pairwise constraints, which overlook the global perspective, i.e., in the ideal case, the pairwise constraint matrix and the ideal similarity matrix possess the same low-rank structure. To this end, we first propose a novel semi-supervised SNMF model by seeking low-rank representation for the tensor synthesized by the pairwise constraint matrix and a similarity matrix obtained by the product of the embedding matrix and its transpose, which could strengthen those two matrices simultaneously from a global perspective. We then propose an enhanced SNMF model, making the embedding matrix tailored to the above tensor low-rank representation. We finally refine the similarity matrix by the strengthened pairwise constraints. We repeat the above steps to continuously boost the similarity matrix and pairwise constraint matrix, leading to a high-quality embedding matrix. Extensive experiments substantiate the superiority of our method. The code is available at https://***/JinaLeejnl/TSNMF.

关键词： Tensors Symmetric matrices Matrix decomposition Sparse matrices Matrix converters Three-dimensional displays Symbols Circuits and systems Vectors Laplace equations Symmetric non-negative matrix factorization tensor low-rank representation semi-supervised clustering

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：