检索结果-内蒙古大学图书馆

Adaptive disentangled target representation for unsupervised domain adaptation in remote sensing segmentation

Engineering applications of Artificial Intelligence 2025年 156卷

作者： Lu, Runuo Dong, Shoubin Jia, Jianxin Wang, Xusheng Liu, Kai Chen, Jinsong Guo, Shanxin Zheng, Xiaorou Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou510641 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute EspooFI-02150 Finland Center for Geo-Spatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application Shenzhen518055 China

Due to the significant differences between the source and target domains, semantic segmentation models for remote sensing images trained on the source domain often struggle to generalize effectively to new target domains, leading to performance degradation. Most solutions disentangle features into domain-invariant features shared by both domains and domain-specific features unique to each domain, relying primarily on the domain-invariant features for model construction and inference. However, during this process, critical domain-specific features as essential information are often discarded as noise, leading to a reduction in segmentation accuracy. To address these issues, this study proposes an unsupervised domain adaptation, called ChameleonRS. ChameleonRS separates the domain-invariant features and the domain-specific features by disentanglement learning, and introduces a multi-level feature alignment module to enhance the representation of domain-invariant features. More importantly, it aligns predictions based on domain-invariant features with those based on fused invariant and specific features using contrastive learning, effectively capturing target-specific features. This study explores two cross-domain semantic segmentation tasks: (I) Geographic location variation. (II) Geographic location and imaging mode variation. Results show that under setting (I), ChameleonRS outperforms the state-of-the-art method by 4.79% in Intersection over Union (IoU) and 6.51% in the F1 score. Under setting (II), it achieves improvements of 4.46% and 4.82% in IoU and F1 score. Results demonstrate the superiority and adaptability of ChameleonRS under varying geographical and imaging conditions, effectively mitigating the generalization issues caused by distribution differences, and thereby promoting the development and application of remote sensing technologies in practical scenarios. © 2025 Elsevier Ltd

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

SR-GAN: Semantic rectifying generative adversarial network for zero-shot learning

arXiv

引用

arXiv 2019年

作者： Ye, Zihan Lyu, Fan Li, Linyan Fu, Qiming Ren, Jinchang Hu, Fuyuan Suzhou University of Science and Technology China Tianjin University China Suzhou Institute of Trade & Commerce China University of Strathclyde United Kingdom Virtual Reality Key Laboratory of Intelligent Interaction and Application Technology of Suzhou China Key Laboratory of Intelligent Building Energy Efficiency China Suzhou Key Laboratory for Big Data and Information Service China

The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper, we propose to classify unseen image by rectifying the semantic space guided by the visual space. First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss. Then, a Semantic Rectifying Generative Adversarial Network (SR-GAN) is built to generate plausible visual feature of unseen class from both semantic feature and rectified semantic feature. To guarantee the effectiveness of rectified semantic features and synthetic visual features, a pre-reconstruction and a post reconstruction networks are proposed, which keep the consistency between visual feature and semantic feature. Experimental results demonstrate that our approach significantly outperforms the state-of-the-arts on four benchmark datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

arXiv

引用

arXiv 2019年

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation & Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https: ACM ISBN 978-1-4503-2138-9. Copyright © 2019, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Parameter prediction method of SAR target simulation based on convolutional neural networks 12

Parameter prediction method of SAR target simulation based o...

引用

12th European Conference on Synthetic Aperture Radar, EUSAR 2018

作者： Shengren, Niu Xiaolan, Qiu Lingxiao, Peng Bin, Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute ofElectronics Chinese Academy of Sciences University of Chinese Academy of Sciences China Suzhou Institute Institute of Electronics Chinese Academy of Sciences China

ISBN: (纸本)9783800746361

SAR image simulation plays a useful role in SAR target interpretation and recognition. The current SAR target simulation methods require high precision of models and simulation parameters, and are only forward processes which lack the feedback adjustment of real image. In this paper, a method of predicting simulation parameters from real images is proposed, which is based on convolutional neural networks(CNN). The architecture and the loss function of the CNN are modified to obtain better performance of the parameter inversion. From the simulation results, the predicted parameters improve the similarity between the simulation images and the real images. © VDE VERLAG GMBH Â Berlin Â Offenbach.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Joint Learning for Non-standard Chinese Building Address Standardization*

Joint Learning for Non-standard Chinese Building Address Sta...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Xue-feng Xi Lei Wang Encen Zou Cheng Zeng Baochuan Fu School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou China VR Key Laboratory of Intelligent Interaction and Application Technology Suzhou China Intelligence Center of KunShan Public Security Bureau KunShan China

ISBN: (纸本)9781538659601;9781538659595

Since there is no uniform specification for building address name in China, the same building address maybe has many different representations in Chinese natural language. The goal of the non-standard Chinese building address standardization task is to uniformly convert the non-standard building addresses from different social institutions to the standard building address defined by the public security organ, so that the spatial location information corresponding to the standard building address can be obtained. This plays an important role in the analysis and processing of big data in smart cities. Due to the large number of non-standard building addresses and the semantic ambiguity of addresses expressed in Chinese natural language, traditional methods based on string matching are difficult to meet the task requirements. To address these above problems, we propose an innovative joint learning approach based on hash map principle and word frequency theory for standardizing Chinese non-standard building addresses. Experimental results on the dataset constructed via crowdsourced technology show that approach has outstanding accuracy and adaptability to data from different sources.

关键词： Standards Buildings Dictionaries Security Task analysis Urban areas

来源：评论

学校读者我要写书评

暂无评论

Transform-invariant convolutional neural networks for image classification and search 24

Transform-invariant convolutional neural networks for image ...

引用

24th ACM Multimedia Conference, MM 2016

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia

ISBN: (纸本)9781450336031

Convolutional neural networks (CNNs) have achieved stateof-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transforminvariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. © 2016 ACM.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Active transfer learning of matching query results across multiple sources

引用

Frontiers of Computer Science 2015年第4期9卷 595-607页

作者： Jie XIN Zhiming CUI Pengpeng ZHAO Tianxu HE The Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China

Entity resolution （ER） is the problem of identi- fying and grouping different manifestations of the same real world object. Algorithmic approaches have been developed where most tasks offer superior performance under super- vised learning. However, the prohibitive cost of labeling training data is still a huge obstacle for detecting duplicate query records from online sources. Furthermore, the unique combinations of noisy data with missing elements make ER tasks more challenging. To address this, transfer learning has been adopted to adaptively share learned common structures of similarity scoring problems between multiple sources. Al- though such techniques reduce the labeling cost so that it is linear with respect to the number of sources, its random sam- piing strategy is not successful enough to handle the ordinary sample imbalance problem. In this paper, we present a novel multi-source active transfer learning framework to jointly select fewer data instances from all sources to train classi- fiers with constant precision/recall. The intuition behind our approach is to actively label the most informative samples while adaptively transferring collective knowledge between sources. In this way, the classifiers that are learned can be both label-economical and flexible even for imbalanced or quality diverse sources. We compare our method with the state-of-the-art approaches on real-word datasets. Our exper- imental results demonstrate that our active transfer learning algorithm can achieve impressive performance with far fewerlabeled samples for record matching with numerous and var- ied sources.

关键词： entity resolution active learning transfer learn-ing convex optimization

来源：评论

学校读者我要写书评

暂无评论

Consensus algorithms for biased labeling in crowdsourcing

引用

information Sciences 2017年 382-383卷 254-273页

作者： Jing Zhang Victor S. Sheng Qianmu Li Jian Wu Xindong Wu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 P. R. China Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing 210094 P. R. China Department of Computer Science University of Central Arkansas Conway AR 72035 USA Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 P. R. China Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 P. R. China School of Computing and Informatics University of Louisiana at Lafayette LA 70504 USA

Although it has become an accepted lay view that when labeling objects through crowdsourcing systems, non-expert annotators often exhibit biases, this argument lacks sufficient evidential observation and systematic empirical study. This paper initially analyzes eight real-world datasets from different domains whose class labels were collected from crowdsourcing systems. Our analyses show that biased labeling is a systematic tendency for binary categorization; in other words, for a large number of annotators, their labeling qualities on the negative class (supposed to be the majority) are significantly greater than are those on the positive class (minority). Therefore, the paper empirically studies the performance of four existing EM-based consensus algorithms , DS, GLAD, RY, and ZenCrowd, on these datasets. Our investigation shows that all of these state-of-the-art algorithms ignore the potential bias characteristics of datasets and perform badly although they model the complexity of the systems. To address the issue of handling biased labeling, the paper further proposes a novel consensus algorithm, namely adaptive weighted majority voting (AWMV), based on the statistical difference between the labeling qualities of the two classes. AWMV utilizes the frequency of positive labels in the multiple noisy label set of each example to obtain a bias rate and then assigns weights derived from the bias rate to negative and positive labels. Comparison results among the five consensus algorithms (AWMV and the four existing) show that the proposed AWMV algorithm has the best overall performance. Finally, this paper notes some potential related topics for future study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circuit tolerance design by differential evolution with hybrid analysis method

Circuit tolerance design by differential evolution with hybr...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Fugui Zhong Bin Li Bo Yuan CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Hefei China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems USTC-Birmingham Joint Research Institute in Intelligent Computation and Its Applications (UBRI) University of Science and Technology of China Hefei China USTC-Birmingham Joint Research Institute in Intelligent Computation and Its Applications (UBRI) University of Science and Technology of China Hefei China

With the continued scaling down of electronic device dimensions, circuit design under parameter variations has received increasing interests. In this paper, a new method that combine the differential evolution with hybrid analysis method is presented to solve the worst-case circuit tolerance design problem. The hybrid analysis method is comprised of two commonly used worst-case circuit tolerance analysis approaches, vertex analysis and Monte Carlo analysis. The search direction of differential evolution is leaded by vertex analysis at the first stage, through which we can reduce the computational complexity of fitness calculation dramatically. Monte Carlo analysis, a higher accuracy analysis method, is applied to ensure the quality of the solutions at the second stage. Some of the individuals are reinitialized to enhance the diversity of the population at the beginning of the second stage. By cooperating the two analysis methods, the proposed method can converge to the global optimum or near-optimum solutions more quickly. The experiment results show the effectiveness and efficiency of proposed techniques for the circuit tolerance design.

关键词： Monte Carlo methods Algorithm design and analysis Sociology Uncertainty Upper bound Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A nonlocal interferometric phase filtering strategy for practical InSAR system

A nonlocal interferometric phase filtering strategy for prac...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xue Lin Dongsheng Fang Fangfang Li Ke Wang Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan China School of Information Science and Engineering University of Jinan Jinan China Institute of Electronics Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China School of Information Science and Engineering Henan University of Technology Zhengzhou China

Nonlocal interferometric phase filtering methods achieve excellent performance in both noise reduction and texture preservation, even in the case of complicated topography and low coherence. The main limitation of the nonlocal methods is the computational burden. This paper proposed a nonlocal phase filtering strategy for the practical InSAR system, which combine the nonlocal algorithm with the traditional method to improve the efficiency.

关键词： Filtering Coherence Noise reduction Frequency estimation Estimation Algorithm design and analysis Surfaces

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：