检索结果-内蒙古大学图书馆

TeCCo: A Terminal-Cloud Cross-Domain Collaborative Framework for remote sensing Image Classification

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Zhang, Ting Cheng, Peirui Zhao, Liangjin Wang, Zhirui Kong, Lingyu Liu, Chenglong Xu, Guangluan Sun, Xian Chinese Acad Sci Aerosp Informat Res Inst Key Lab Target Cognit & Applicat Technol TCAT Beijing Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China

The terminal-cloud collaborative framework boosts precision and efficiency by integrating cloud computing power with low-latency terminal responsiveness, offering a suitable solution for the growing demands of multiplatform remote sensing (RS) image interpretation. However, the significant differences in data distribution across various RS platforms present a great challenge in balancing the cloud's centralized processing capabilities with the local interpretation abilities of different terminals. To address this challenge, we propose a terminal-cloud cross-domain collaborative (TeCCo) framework that inherits the efficiency advantages of multiple platforms while ensuring high-accuracy interpretation of diverse data distributions from different terminals. First, the dual classifier co-learning (DCCL) module is designed to enhance cloud robustness. By combining a multilayer perceptron for instance-level classification and a graph convolutional network (GCN) for feature-level aggregation, it achieves mutual supervision and improves feature alignment across different data distributions. Second, the hypernetwork personalization (HNP) module is introduced to generate personalized classifier parameters for each terminal with little fine-tuning cost, allowing terminals to maintain their uniqueness while benefiting from the generalization advantages of collaborative training. Finally, a data-assisted progressive inference mechanism is proposed to enhance accuracy by jointly clustering the features transmitted from terminals and the features of supervised data in the cloud. Extensive experiments demonstrate that TeCCo effectively addresses data distribution challenges, enhancing both the generalization of the cloud model and the personalization of terminal models, achieving state-of-the-art (SOTA) performance in cross-domain and multiplatform RS image classification.

关键词： Collaboration Training Cloud computing Accuracy Data models Adaptation models Image classification Robustness Inference mechanisms Feature extraction Domain adaptation multiplatform image classification remote sensing (RS) terminal-cloud collaboration

来源：评论

学校读者我要写书评

暂无评论

Multibranch Fusion-Based Feature Enhance for remote-sensing Scene Classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Lu, Xiongbo Yang, Meng Chen, Yaxiong Xiong, Shengwu Lu, Xiaoqiang Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Interdisciplinary Artificial Intelligence Res Inst Wuhan Coll Wuhan 430212 Peoples R China Qiongtai Normal Univ Sch Informat Sci & Technol Haikou 571127 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350108 Peoples R China

remote-sensing (RS) scene classification is a fundamental and significant task in RS image interpretation, involving the annotation of semantic content. RS scene images are characterized by complex backgrounds, rich content, and multiscale targets, exhibiting both intraclass separation and interclass convergence. Therefore, extracting features that effectively express the intrinsic attributes of images and possess high discriminative is crucial for RS scene classification. Existing global-based methods often lack the ability to capture significant detailed information in similar scenes. Conversely, methods based on local discriminative features tend to overlook the interrelationships of objects within the same scene. To address these issues, this article proposes a unified framework named MBFNet to align and fuse features of different scales and levels for accurate RS scene classification. We utilize a multibranch feature-extracting network structure with parallel convolution and Transformer modules. Simultaneously, a kernel-selected multiscale aggregation (KSMSA) module is designed to efficiently process the diverse scale features emanating from these parallel branches. By selecting different convolution kernels, a dynamic receptive field is established to adaptively process features of different scales, reducing semantic differences to achieve effective aggregation of multiscale features. Moreover, a learnable multilevel aggregation (LMLA) module is designed to integrate shallow features, such as shape information, into deep features for more comprehensive feature fusion. Benefiting from KSMSA and LMLA, the proposed MBFNet improves the discriminability of features, thereby enhancing classification performance. Comprehensive experiments on three benchmark datasets demonstrate that the proposed method outperforms state-of-the-art RS scene classification methods in terms of performance.

关键词： Feature fusion multilevel aggregation multiscale aggregation multiscale aggregation remote-sensing (RS) remote-sensing (RS) scene classification scene classification scene classification

来源：评论

学校读者我要写书评

暂无评论

Chiroptical sensing for remote chiral amines via a C-H activation reaction

引用

CHINESE CHEMICAL LETTERS 2025年第5期36卷

作者： Li, Xin Lu, Jia-Min Li, Bo Zhao, Chen Yang, Bei-Bei Li, Li Chinese Acad Med Sci & Peking Union Med Coll State Key Lab Digest Hlth Beijing Key Lab Act Subst Discovery & Druggabil Ev Inst Mat Med Beijing 100050 Peoples R China

An electronic circular dichroism (ECD)-based chiroptical sensing method has been developed for beta- and gamma-chiral primary amines via a C-H activation reaction. With the addition of Pd(OAc)2, the flexible remote chiral primary amine fragment in the bidentate ligand intermediate was fixed to form a cyclopalladium complex, producing an intense ECD response. The correlation between the sign of Cotton effects and the absolute configuration of substrates was proposed, together with theoretical verification using time- dependent density functional theory (TDDFT). Chiroptical sensing of an important drug raw material was performed to provide rapid and accurate information on the absolute optical purity. This work introduces an alternative perspective of C-H activation reaction as well as a feasible chiroptical sensing method of remote chiral amines. (c) 2025 Published by Elsevier B.V. on behalf of Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences.

关键词： Electronic circular dichroism (ECD) remote chiral amines C-H activation Cyclo-palladium Absolute optical purity

来源：评论

学校读者我要写书评

暂无评论

Bilinear Parallel Fourier Transformer for Multimodal remote sensing Classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Chen, Yaxiong Wang, Qicong Zhao, Yichen Xiong, Shengwu Lu, Xiaoqiang Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Wuhan Coll Interdisciplinary Artificial Intelligence Res Inst Wuhan 430212 Peoples R China Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350108 Peoples R China

Vision Transformers (ViTs) have shown promise in multimodal fusion image classification, yet face performance challenges in complex remote sensing scenarios. Single fusion frameworks often fail to fully utilize multimodal diversity, and the uneven distribution of image categories complicates the accurate construction of spatial structures by Transformers. Additionally, traditional cross-entropy tends to favor majority classes, neglecting minority classes, resulting in suboptimal predictions and reduced overall accuracy (OA). To solve these challenges, we propose a novel deep neural network, a bilinear parallel Fourier Transformer (BPFT). We propose a novel dual-fusion feature interaction (DFFI) module that utilizes two distinct types of fused features for learning, namely the spatial-spectral fusion feature and the global fusion feature. Besides, we introduce a dual-feature interaction (DFI) module to improve the utilization of fused feature information. To enable the Transformer to better establish spatial structural relationships, we employ the Fourier transform in place of the self-attention mechanism. To address the focus on minority class labels, we propose an exponential label smoothing cross-entropy loss function. This loss function comprises two components: exponential cross-entropy and label smoothing. The exponential cross-entropy component applies a strong penalty to misclassified samples, thereby increasing attention on minority class labels. To validate the efficacy of our approach, extensive experiments are conducted across two multimodal remote sensing datasets: Augsburg and Berlin, encompassing hyperspectral imaging (HSI) data and synthetic aperture radar (SAR) data. The results of these experiments affirm the superior performance of our proposed BPFT model compared to existing state-of-the-art models in multimodal remote sensing image classification tasks.

关键词： Transformers remote sensing Feature extraction Image classification Data mining Artificial intelligence Fourier transforms Data models Convolutional neural networks Accuracy Cross-modal retrieval prior similarity saliency learning

来源：评论

学校读者我要写书评

暂无评论

From Macro to Micro: A Lightweight Interleaved Network for remote sensing Image Change Detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Xu, Yetong Lei, Tao Ning, Hailong Lin, Shaoxiong Liu, Tongfei Gong, Maoguo Nandi, Asoke K. Shaanxi Univ Sci & Technol Shaanxi Joint Lab Artificial Intelligence Xian 710021 Peoples R China Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710121 Peoples R China Xidian Univ Key Lab Collaborat Intelligence Syst Minist Educ Xian 710071 Peoples R China Brunel Univ London Dept Elect & Elect Engn Uxbridge UB8 3PH England

remote sensing image change detection (RSICD) is a crucial technology for Earth monitoring, but it faces two major challenges in practical applications. First, the complex scenes in remote sensing (RS) images make it difficult to accurately locate and distinguish the small change targets. Second, most RSICD methods usually stack complex modules to improve model performance, which inevitably leads to high computational costs. To address these issues, this article proposes a lightweight interleaved network from macro to micro for RSICD, named M2M-LINet. First, a three-stage RSICD framework inspired by holistic registration theory in biological vision is designed to deal with complex and small change targets. Specifically, the first stage is the coarse location stage to obtain a coarse localization on change targets, which is similar to the macroscopic observation of human eyes. The second stage is the fine detail focusing stage for capturing fine-grained information by designing a CNN-Transformer interleaved model, which is akin to the microscopic observation of the human eye. The third stage is the decoding prediction stage for predicting the final change features by mimicking the human interpretation of change information. Second, a lightweight interleaved structure is designed in the fine detail focusing stage to reduce the model size for facilitating deployment. It consists of two critical lightweight components. One is the lightweight convolutional block (LCB) that is devised to enhance high-frequency and low-frequency information for fine-grained change localization. The other is the lightweight Transformer block (LTB) that is designed as a linear self-attention mechanism to integrate multiscale information into feature maps effectively. The experiments on three RSICD datasets demonstrate that the proposed method performs excellently for complex change scenes and small change targets and significantly reduces the consumption of computing resources.

关键词： Transformers Feature extraction Computer architecture Computational modeling Accuracy Convolutional neural networks Attention mechanisms Data mining Aggregates Sensors Change detection (CD) lightweight remote sensing (RS) image Transformer

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Unmanned Aerial Vehicle remote sensing Images Using SegFormer 4th

Semantic Segmentation of Unmanned Aerial Vehicle Remote Sens...

引用

4th International conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Spasev, Vlatko Dimitrovski, Ivica Chorbev, Ivan Kitanovski, Ivan Univ Ss Cyril & Methodius Fac Comp Sci & Engn Skopje North Macedonia

ISBN: (纸本)9783031821554;9783031821561

The escalating use of Unmanned Aerial Vehicles (UAVs) as remote sensing platforms has garnered considerable attention, proving invaluable for ground object recognition. While satellite remote sensing images face limitations in resolution and weather susceptibility, UAV remote sensing, employing low-speed unmanned aircraft, offers enhanced object resolution and agility. The advent of advanced machine learning techniques has propelled significant strides in image analysis, particularly in semantic segmentation for UAV remote sensing images. This paper evaluates the effectiveness and efficiency of SegFormer, a semantic segmentation framework, for the semantic segmentation of UAV images. SegFormer variants, ranging from real-time (B0) to high-performance (B5) models, are assessed using the UAVid dataset tailored for semantic segmentation tasks. The research details the architecture and training procedures specific to SegFormer in the context of UAV semantic segmentation. Experimental results showcase the model's performance on benchmark dataset, highlighting its ability to accurately delineate objects and land cover features in diverse UAV scenarios, leading to both high efficiency and performance.

关键词： Semantic segmentation Deep learning SegFormer UAV images

来源：评论

学校读者我要写书评

暂无评论

A hidden multiwing memristive neural network and its application in remote sensing data security

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 277卷

作者： Ding, Sirui Lin, Hairong Deng, Xiaoheng Yao, Wei Jin, Jie Xinjiang Univ Sch Software Urumqi 830091 Peoples R China Cent South Univ Sch Elect Informat Changsha 410083 Peoples R China Cent South Univ Shenzhen Res Inst Shenzhen 518000 Peoples R China Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Peoples R China Hunan Univ Sci & Technol Sch Informat & Elect Engn Xiangtan 411201 Peoples R China

Chaotic neural networks have important applications in the field of information security. However, traditional chaotic neural networks often fall short of meeting the security requirements for high-security encryption scenarios due to insufficient complexity in their chaotic dynamics. In this paper, we present a novel chaotic memristive neural network (MNN) that integrates two memristors into a traditional Hopfield neural network. A distinctive feature of this MNN is its ability to generate highly complex hidden multiwing chaotic attractors. The characteristics and generation mechanisms of the hidden multiwing attractors are revealed by adopting various dynamics analysis methods. The analysis results show that by adjusting the memristors' control parameters, the number of wings in the hidden multiwing memristive neural network (HM-MNN) can be easily controlled. Meanwhile, we develop a digital hardware platform to further verify the numerical simulation results. Furthermore, a highly efficient encryption algorithm is developed based on the presented HM-MNN. Then the secure algorithm is successfully applied in remote sensing system to protect image data privacy. Security performance analysis shows that by leveraging the complex dynamics and unpredictability of the HMMNN, the designed encryption algorithm can ensure entropy reach 7.9999 and large key space(2432), making the encrypted images resilient against various attacks and providing a secure method for transmitting and storing sensitive remote sensing data.

关键词： Chaotic system Hidden attractor Multiwing attractor Memristive neural network Image encryption

来源：评论

学校读者我要写书评

暂无评论

Change Detection Meets Frequency Learning: A Coarse-to-Fine Dual-Domain Detection Network

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Zhang, Wenbo Guo, Wenjin Li, Yunsong Xie, Weiying Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China

Change detection (CD) aims to distinguish the changed regions in bitemporal images under the same area. Accurate detection needs comprehensive and precise semantic information extraction. Naturally, multiscale feature extraction becomes a fashion. Recent methods implement multiscale feature extraction through complicated convolutional neural network (CNN) modules or Transformers. However, complicated modules are far from the practical demands. First, implementing multiscale feature extraction through multilevel stacking of modules leads to unnecessary computing. Not all regions in images need very detailed detection. Second, respective modules for different scale extractions make discrete resolutions on detection. We need a more continuous recognition of spatial resolutions. Third, inherent weakness in high-frequency learning of CNNs and Transformers degrades the detection of details. In this article, we develop a new multiscale architecture, cross-domain coarse-to-fine (CDC2F) network. Specifically, we first perform coarse detection in the spatial domain. Based on the coarse change map (CM), the bitemporal images will be segmented into blocks, which are then go through a filtering process to retain the mixed blocks. For the retained blocks, a fine detection will be conducted in the frequency domain. Finally, spatial-frequency features are fused to make the final detection. The proposed coarse-to-fine (C2F) strategy guarantees computational efficiency. The cross-domain architecture (spatial and frequency) provides a continuous scale recognition through discrete cosine transform (DCT). And the explicit frequency learning makes detailed detection come true. Extensive experiments on three widely used CD datasets [learning, vision, and remote sensing CD (LEVIR-CD), Wuhan University (WHU), and season-varying CD (SVCD)] show that CDC2F achieves state-of-the-art (SOTA) performance in both the evaluation metrics and the visual presentation, with few parameters and low compu

关键词： Feature extraction Frequency-domain analysis Transformers remote sensing Semantics Discrete cosine transforms Data mining Lighting Convolutional neural networks Spatial resolution Change detection (CD) convolutional neural network (CNN) deep learning frequency domain remote sensing Transformer

来源：评论

学校读者我要写书评

暂无评论

A Review on Synergizing Convolutional and Swin Transformer Approaches for Superior remote sensing Detection 6

A Review on Synergizing Convolutional and Swin Transformer A...

引用

6th International conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Reddy, Allipurapu Meghanath Gangadhara, Sai Likhith Reddy, R. Ravinder Padmalatha, E. Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (纸本)9798331522667

remote sensing object detection plays a crucial role in environmental monitoring, yet traditional methods often face difficulties with varying object scales, intricate backgrounds, and densely populated small objects. This research study elaborates on various methodologies carried out in the remote sensing detection area, with the support of the latest advances in traditional and deep learning techniques. We make a critical presentation of CNNs, Swin Transformers, and hybrid models, their adaptations, benefits, and limitations. performance metrics along with adaptability across different datasets and environments are presented through comparative analysis of various models. The paper provides in-depth analysis into the ever-changing landscape of remote sensing technologies and the latest tangible applications regarding such technologies. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Spaceborne Neural Network Accelerator and Its Fault Tolerance Design

引用

remote sensing 2025年第1期17卷 69-69页

作者： Shao, Yingzhao Wang, Junyi Han, Xiaodong Li, Yunsong Li, Yaolin Tao, Zhanpeng Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China China Acad Space Technol Xian Xian 710100 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China

To meet the high-reliability requirements of real-time on-orbit tasks, this paper proposes a fault-tolerant reinforcement design method for spaceborne intelligent processing algorithms based on convolutional neural networks (CNNs). This method is built on a CNN accelerator using Field-Programmable Gate Array (FPGA) technology, analyzing the impact of Single-Event Upsets (SEUs) on neural network computation. The accelerator design integrates data validation, Triple Modular Redundancy (TMR), and other techniques, optimizing a partial fault-tolerant architecture based on SEU sensitivity. This fault-tolerant architecture analyzes the hardware accelerator, parameter storage, and actual computation, employing data validation to reinforce model parameters and spatial and temporal TMR to reinforce accelerator computations. Using the ResNet18 model, fault tolerance performance tests were conducted by simulating SEUs. Compared to the prototype network, this fault-tolerant design method increases tolerance to SEU error accumulation by five times while increasing resource consumption by less than 15%, making it more suitable for spaceborne on-orbit applications than traditional fault-tolerant design approaches.

关键词： spaceborne computing single-event upset convolutional neural network field-programmable gate array fault-tolerant design

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：