Query：
学者姓名：郑向涛
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Remote-sensing fine-grained ship classification (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification methods. Recent advancements in large pretrained vision-language models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, particularly in understanding image content. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories, which holds considerable significance in scenarios with restricted data due to cost or privacy constraints. Directly fine-tuning VLMs for RS-FGSC often encounters the challenge of overfitting the seen classes, resulting in suboptimal generalization to unseen classes, which highlights the difficulty in differentiating complex backgrounds and capturing distinct ship features. To address these issues, we introduce a novel prompt tuning technique that employs a hierarchical, multigranularity prompt design. Our approach integrates remote sensing ship priors through bias terms, learned from a small trainable network. This strategy enhances the model's generalization capabilities while improving its ability to discern intricate backgrounds and learn discriminative ship features. Furthermore, we contribute to the field by introducing a comprehensive dataset, FGSCM-52, significantly expanding existing datasets with more extensive data and detailed annotations for less common ship classes. Extensive experimental evaluations demonstrate the superiority of our proposed method over current state-of-the-art techniques. The source code will be made publicly available.
Keyword ：
Adaptation models Adaptation models Computational modeling Computational modeling Data models Data models Feature extraction Feature extraction Generalization Generalization Marine vehicles Marine vehicles Overfitting Overfitting prompt tuning prompt tuning Remote sensing Remote sensing remote sensing image remote sensing image ship classification ship classification Testing Testing Training Training Tuning Tuning vision-language models (VLMs) vision-language models (VLMs)
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lan, Long , Wang, Fengxiang , Zheng, Xiangtao et al. Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| MLA | Lan, Long et al. "Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63 (2025) . |
| APA | Lan, Long , Wang, Fengxiang , Zheng, Xiangtao , Wang, Zengmao , Liu, Xinwang . Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification methods. Recent advancements in large pre-trained Vision-Language Models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, particularly in understanding image content. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories, which holds considerable significance in scenarios with restricted data due to cost or privacy constraints. Directly fine-tuning VLMs for RS-FGSC often encounters the challenge of overfitting the seen classes, resulting in suboptimal generalization to unseen classes, which highlights the difficulty in differentiating complex backgrounds and capturing distinct ship features. To address these issues, we introduce a novel prompt tuning technique that employs a hierarchical, multi-granularity prompt design. Our approach integrates remote sensing ship priors through bias terms, learned from a small trainable network. This strategy enhances the model's generalization capabilities while improving its ability to discern intricate backgrounds and learn discriminative ship features. Furthermore, we contribute to the field by introducing a comprehensive dataset, FGSCM-52, significantly expanding existing datasets with more extensive data and detailed annotations for less common ship classes. Extensive experimental evaluations demonstrate the superiority of our proposed method over current state-of-the-art techniques. The source code will be made publicly available. © 1980-2012 IEEE.
Keyword ：
generalization generalization prompt tuning prompt tuning remote sensing image remote sensing image ship classification ship classification vision-language models vision-language models
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lan, L. , Wang, F. , Zheng, X. et al. Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification [J]. | IEEE Transactions on Geoscience and Remote Sensing , 2024 . |
| MLA | Lan, L. et al. "Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification" . | IEEE Transactions on Geoscience and Remote Sensing (2024) . |
| APA | Lan, L. , Wang, F. , Zheng, X. , Wang, Z. , Liu, X. . Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification . | IEEE Transactions on Geoscience and Remote Sensing , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
遥感对地观测中普遍存在多平台、多传感器和多角度的多源数据，为遥感场景解译提供协同互补信息。然而，现有的场景解译方法需要根据不同遥感场景数据训练模型，或者对测试数据标准化以适应现有模型，训练成本高、响应周期长，已无法适应多源数据协同解译的新阶段。跨域遥感场景解译将已训练的老模型迁移到新的应用场景，通过模型复用以适应不同场景变化，利用已有领域的知识来解决未知领域问题。本文以跨域遥感场景解译为主线，综合分析国内外文献，结合场景识别和目标识别两个典型任务，论述国内外研究现状、前沿热点和未来趋势，梳理总结跨域遥感场景解译的常用数据集和统一的实验设置。本文实验数据集及检测结果的公开链接为：https://github.com/XiangtaoZheng/CDRSSI。
Keyword ：
分布外泛化 分布外泛化 多样性数据集 多样性数据集 模型泛化 模型泛化 自适应算法 自适应算法 跨域遥感场景解译 跨域遥感场景解译 迁移学习 迁移学习
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郑向涛 , 肖欣林 , 陈秀妹 et al. 跨域遥感场景解译研究进展 [J]. | 中国图象图形学报 , 2024 , 29 (06) : 1730-1746 . |
| MLA | 郑向涛 et al. "跨域遥感场景解译研究进展" . | 中国图象图形学报 29 . 06 (2024) : 1730-1746 . |
| APA | 郑向涛 , 肖欣林 , 陈秀妹 , 卢宛萱 , 刘小煜 , 卢孝强 . 跨域遥感场景解译研究进展 . | 中国图象图形学报 , 2024 , 29 (06) , 1730-1746 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In remote sensing of Earth observation, multi-source data can be captured by multiple platforms, multiple sensors, and multiple perspectives. These data provide complementary information for interpreting remote sensing scenes. Although these data offer richer information, they also increase the demand for model depth and complexity. Deep learning plays a pivotal role in unlocking the potential of remote sensing data by delving deep into the semantic layers of scenes and extracting intricate features from images. Recent advancements in artificial intelligence have greatly enhanced this process. However, deep learning networks have limitations when applied to remote sensing images. 1)The huge number of parameters and the difficulty in training, as well as the over-reliance on labeled training data, can affect these images. Remote sensing images are characterized by“data miscellaneous marking difficulty”, which makes manual labeling insufficient for meeting the training needs of deep learning. 2)Variations in remote sensing platforms, sensors, shooting angles, resolution, time, location, and weather can all impact remote sensing images. Thus, the interpreted images and training samples cannot have the same distribution. This inconsistency results in weak generalization ability in existing models, especially when dealing with data from different distributions. To address this issue, cross-domain remote sensing scene interpretation aims to train a model on labeled remote sensing scene data(source domain)and apply it to new, unlabeled scene data(target domain)in an appropriate way. This approach reduces the dependence on target domain data and relaxes the assumption of the same distribution in existing deep learning tasks. The shallow layers of convolutional neural networks can be used as general-purpose feature extractors, but deeper layers are more task-specific and may introduce bias when applied to other tasks. Therefore, the migration model must be modified to accomplish the task of interpreting the target domain. Cross-domain interpretation tasks aim to establish a model that can adapt to various scene changes by utilizing migration learning, domain adaptation and other techniques for reducing model prediction inaccuracy caused by changes in the data domain. This approach improves the robustness and generalization ability of the model. Interpreting cross-domain remote sensing scenes typically requires using data from multiple remote sensing sources, including radar, aerial and satellite imagery. These images may have varying views, resolutions, wavelength bands, lighting conditions and noise levels. They may also originate from different locations or sensors. As the Global Earth Observation Systems continues to advance, remote sensing images now include cross-platform, cross-sensor, cross-resolution, and cross-region, which results in enormous distributional variances. Therefore, the study of cross-domain remote sensing scene interpretation is essential for the commercial use of remote sensing data and has theoretical and practical importance. This report categorizes scene decoding tasks into four main types based on the labeled set of data：methods based on closed-set domain adaptation, partial-domain adaptation, open-set domain adaptation and generalized domain adaptation. Approaches based on closed-set domain adaptation focus on tasks where the label set of the target domain is the same as that of the source domain. Partial domain adaptation focuses on tasks where the label set of the target domain is a subset of the source domain. Open-set domain adaptation aims to research tasks where the label set of the source domain is a subset of the label set of the target domain, and it does not apply restrictions in the approach of generalized domain adaptation. This study provides an in-depth investigation of two typical tasks in cross-domain remote sensing interpretation：scene recognition and target knowledge. The first part of the study utilizes domestic and international literature to provide a comprehensive assessment of the current research status of the four types of methods. Within the target recognition task, cross-domain tasks are further subdivided into cross-domain for visible light data and cross-domain from visible light to Synthetic Aperture Radar images. After a quantitative analysis of the sample distribution characteristics of different datasets, a unified experimental setup for cross-domain tasks is proposed. In the scene classification task, the dataset is explored by classifying it according to the label set categorization, and specific examples are given to provide the corresponding experimental setup for the readers’reference. The fourth part of the study discusses the research trends in cross-domain remote sensing interpretation, which highlights four challenging research directions：few-shot learning, source domain data selection, multi-source domain interpretation, and cross-modal interpretation. These areas will be important directions for the future development of remote sensing scene interpretation, which offers potential choices for readers’subsequent research directions. © 2024 Editorial and Publishing Board of JIG. All rights reserved.
Keyword ：
adaptive algorithm adaptive algorithm cross-domain remote sensing scene interpretation cross-domain remote sensing scene interpretation diverse dataset diverse dataset migration learning migration learning model generalization model generalization out-of-distribution generalization out-of-distribution generalization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, X. , Xiao, X. , Chen, X. et al. Advancements in cross-domain remote sensing scene interpretation; [跨域遥感场景解译研究进展] [J]. | Journal of Image and Graphics , 2024 , 29 (6) : 1730-1746 . |
| MLA | Zheng, X. et al. "Advancements in cross-domain remote sensing scene interpretation; [跨域遥感场景解译研究进展]" . | Journal of Image and Graphics 29 . 6 (2024) : 1730-1746 . |
| APA | Zheng, X. , Xiao, X. , Chen, X. , Lu, W. , Liu, X. , Lu, X. . Advancements in cross-domain remote sensing scene interpretation; [跨域遥感场景解译研究进展] . | Journal of Image and Graphics , 2024 , 29 (6) , 1730-1746 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着遥感成像技术的不断进步,遥感图像的舰船目标检测已成为确保海上运输安全和效率的关键手段,对海上交通、环境保护及国家安全至关重要.然而,由于舰船目标尺度差异大、背景复杂等问题,现有单一检测模型的方法过度依赖训练数据,无法适应尺度多变的舰船目标.提出了一种多模型协同训练的框架,利用多个已训练好的舰船检测模型作为辅助网络,通过知识迁移的方式辅助优化目标数据的主网络.首先,通过三元关系约束建立辅助网络与主网络间的分布知识传递;其次,采用软标签引导策略整合辅助网络中的标签知识,提高舰船检测的准确性.实验结果表明:相较于现有主流方法,所提方法在DOTA和xView数据集上展示了较好的性能,克服了单一模型的局限性,为遥感图像的目标检测提供了新的解决思路.
Keyword ：
多尺度表达 多尺度表达 多模型协同 多模型协同 目标检测 目标检测 知识融合 知识融合 舰船识别 舰船识别
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 肖欣林 , 施伟超 , 郑向涛 et al. 基于多模型协同的舰船目标检测 [J]. | 航空学报 , 2024 , 45 (14) : 73-83 . |
| MLA | 肖欣林 et al. "基于多模型协同的舰船目标检测" . | 航空学报 45 . 14 (2024) : 73-83 . |
| APA | 肖欣林 , 施伟超 , 郑向涛 , 高跃明 , 卢孝强 . 基于多模型协同的舰船目标检测 . | 航空学报 , 2024 , 45 (14) , 73-83 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In the context of globalization，the importance of ship monitoring is becoming more and more prominent. With the continuous progress of the remote sensing imaging technology，ship detection has become a key means to ensure the safety and efficiency of maritime transportation，and is crucial for maritime transportation，environmental protection，and national security. However，due to the large difference in scales and complex background of ship targets，existing single detection model methods rely too heavily on training data and cannot adapt to ship targets with variable scales. In this paper，we propose a multiple models collaboration framework，in which multiple trained ship detection models are regarded as auxiliary network，and the main network training is optimized by knowledge migration. First，ternary relationship constraints are introduced to transfer knowledge between the auxiliary network and the main network. Then，a soft-label guidance strategy is proposed to further improve the accuracy of ship detection. The experimental results show that compared with the existing mainstream methods，the proposed method demonstrates better performance on DOTA and xView datasets，overcoming the limitation of a single model and providing a new solution idea for target detection in remote sensing images. © 2024 Chinese Society of Astronautics. All rights reserved.
Keyword ：
knowledge fusion knowledge fusion multiple models collaboration multiple models collaboration multi-scale representation multi-scale representation remote sensing remote sensing ship detection ship detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiao, X. , Shi, W. , Zheng, X. et al. Multiple models collaboration for ship detection; [基 于 多 模 型 协 同 的 舰 船 目 标 检 测] [J]. | Acta Aeronautica et Astronautica Sinica , 2024 , 45 (14) . |
| MLA | Xiao, X. et al. "Multiple models collaboration for ship detection; [基 于 多 模 型 协 同 的 舰 船 目 标 检 测]" . | Acta Aeronautica et Astronautica Sinica 45 . 14 (2024) . |
| APA | Xiao, X. , Shi, W. , Zheng, X. , Gao, Y. , Lu, X. . Multiple models collaboration for ship detection; [基 于 多 模 型 协 同 的 舰 船 目 标 检 测] . | Acta Aeronautica et Astronautica Sinica , 2024 , 45 (14) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Detecting land use changes in urban areas from very-high-resolution (VHR) satellite images presents two primary challenges: 1) traditional methods focus mainly on comparing changes in land cover-related features, which are insufficient for detecting changes in land use and are prone to pseudo-changes caused by illumination differences, seasonal variations, and subtle structural changes and 2) spatial structural information, which is characterized by topological relationships among land cover objects, is crucial for urban land use classification but remains underexplored in change detection. To address these challenges, this study developed a local-global structural interaction network (LGSI-Net) based on a Siamese graph neural network (SGNN) that integrates high-level structural and semantic information to detect urban land use changes from bitemporal VHR images. We developed both local structural feature interaction module (LSIM) and global structural feature interaction module (GSIM) to enhance the representation of bitemporal structural features at the global scene graph and local object node levels. Experiments on the publicly available MtS-WH dataset and two generated datasets, LUCD-FZ and LUCD-HF, show that the proposed method outperforms the existing bag of visual word (BoVW)-based method and CorrFusionNet. Furthermore, we evaluated the detection performance for different semantic feature extraction strategies and structural feature extraction backbones. The results demonstrate that the proposed method, which integrates high-level semantic and graph isomorphism network (GIN)-derived structural features achieves the best performance. The method trained on the LUCD-FZ dataset was successfully transferred to the LUCD-HF dataset with different urban landscapes, indicating its effectiveness in detecting land use changes from VHR satellite images, even in areas with relatively large imbalances between changed and unchanged samples.
Keyword ：
Local-global structural interaction Local-global structural interaction Siamese graph neural networks (SGNNs) Siamese graph neural networks (SGNNs) urban land use change detection urban land use change detection very-high-resolution (VHR) satellite images very-high-resolution (VHR) satellite images
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lou, Kangkai , Li, Mengmeng , Li, Fashuai et al. Integrating Local-Global Structural Interaction Using Siamese Graph Neural Network for Urban Land Use Change Detection From VHR Satellite Images [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2024 , 62 . |
| MLA | Lou, Kangkai et al. "Integrating Local-Global Structural Interaction Using Siamese Graph Neural Network for Urban Land Use Change Detection From VHR Satellite Images" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 62 (2024) . |
| APA | Lou, Kangkai , Li, Mengmeng , Li, Fashuai , Zheng, Xiangtao . Integrating Local-Global Structural Interaction Using Siamese Graph Neural Network for Urban Land Use Change Detection From VHR Satellite Images . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2024 , 62 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
It is a challenging task to recognize novel categories with only a few labeled remote-sensing images. Currently, meta-learning solves the problem by learning prior knowledge from another dataset where the classes are disjoint. However, the existing methods assume the training dataset comes from the same domain as the test dataset. For remote-sensing images, test datasets may come from different domains. It is impossible to collect a training dataset for each domain. Meta-learning and transfer learning are widely used to tackle the few-shot classification and the cross-domain classification, respectively. However, it is difficult to recognize novel categories from various domains with only a few images. In this article, a domain mapping network (DMN) is proposed to cope with the few-shot classification under domain shift. DMN trains an efficient few-shot classification model on the source domain and then adapts the model to the target domain. Specifically, dual autoencoders are exploited to fit the source and target domain distribution. First, DMN learns an autoencoder on the source domain to fit the source domain distribution. Then, a target autoencoder is initiated from the source domain autoencoder and further updated with a few target images. To ensure the distribution alignment, cycle-consistency losses are proposed to jointly train the source autoencoder and target autoencoder. Extensive experiments are conducted to validate the generalizable and superiority of the proposed method.
Keyword ：
Adaptation models Adaptation models Cross-domain classification Cross-domain classification few-shot classification few-shot classification Image recognition Image recognition Measurement Measurement meta-learning meta-learning Metalearning Metalearning Remote sensing Remote sensing remote sensing scene classification remote sensing scene classification Task analysis Task analysis Training Training transfer learning transfer learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lu, Xiaoqiang , Gong, Tengfei , Zheng, Xiangtao . Domain Mapping Network for Remote Sensing Cross-Domain Few-Shot Classification [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2024 , 62 . |
| MLA | Lu, Xiaoqiang et al. "Domain Mapping Network for Remote Sensing Cross-Domain Few-Shot Classification" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 62 (2024) . |
| APA | Lu, Xiaoqiang , Gong, Tengfei , Zheng, Xiangtao . Domain Mapping Network for Remote Sensing Cross-Domain Few-Shot Classification . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2024 , 62 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
高空间分辨率、高光谱分辨率、大幅宽与大数据量是高光谱卫星数据发展趋势，传统高光谱影像的像素级分类面临难以处理海量数据、无法高效获取复杂海量影像中隐含信息的困境。已有研究开始关注高光谱影像的场景级分类，并逐步建立完善高光谱遥感场景分类数据集。然而，目前的数据集制作过程多参考高空间分辨率可见光遥感场景数据集的制作方法，主要采用遥感影像的空间信息进行场景类别解译，忽视了高光谱场景的光谱信息。因此，为构建高光谱影像的遥感场景分类数据集，本文利用“珠海一号”高光谱卫星拍摄的西安地区高光谱数据，使用无监督光谱聚类辅助定位、裁剪与标注待选场景样本，结合Google Earth高分影像进行目视筛选，构建6类场景类型和737幅场景样本的珠海一号高光谱场景分类数据集。并基于光谱与空间两个视角开展场景分类实验，通过视觉词袋、卷积神经网络等方法的基准测试结果，对不同算法在现有多光谱和高光谱遥感场景分类数据集下的性能进行深入分析。本研究可为后续的高光谱影像解译研究提供了有力的数据支撑。
Keyword ：
场景分类 场景分类 数据集 数据集 特征提取 特征提取 珠海一号 珠海一号 高光谱遥感 高光谱遥感
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘渊 , 郑向涛 , 卢孝强 . 珠海一号高光谱场景分类数据集 [J]. | 遥感学报 , 2024 , 28 (01) : 306-319 . |
| MLA | 刘渊 et al. "珠海一号高光谱场景分类数据集" . | 遥感学报 28 . 01 (2024) : 306-319 . |
| APA | 刘渊 , 郑向涛 , 卢孝强 . 珠海一号高光谱场景分类数据集 . | 遥感学报 , 2024 , 28 (01) , 306-319 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
高光谱图像分类将每个像素分类至预设的地物类别,对环境测绘等各类地球科学任务有着至关重要的意义.近年来,学者们尝试利用深度学习框架进行高光谱图像分类,取得了令人满意的效果.然而这些方法在光谱特征的提取上仍存在一定缺陷.本文提出一个基于自注意力机制的层级融合高光谱图像分类框架(hierarchical self-attention network,HSAN).首先,构建跳层自注意力模块进行特征学习,利用Transformer结构中的自注意力机制捕获上下文信息,增强有效信息贡献.然后,设计层级融合方式,进一步缓解特征学习过程中的有效信息损失,增强各层级特征联动.在Pavia University及Houston2013数据集上的试验表明,本文提出的框架相较于其他高光谱图像分类框架具有更好的分类性能.
Keyword ：
Transformer Transformer 层级融合 层级融合 自注意力机制 自注意力机制 高光谱图像分类 高光谱图像分类
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张艺超 , 郑向涛 , 卢孝强 . 基于层级Transformer的高光谱图像分类方法 [J]. | 测绘学报 , 2023 , 52 (7) : 1139-1147 . |
| MLA | 张艺超 et al. "基于层级Transformer的高光谱图像分类方法" . | 测绘学报 52 . 7 (2023) : 1139-1147 . |
| APA | 张艺超 , 郑向涛 , 卢孝强 . 基于层级Transformer的高光谱图像分类方法 . | 测绘学报 , 2023 , 52 (7) , 1139-1147 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
