检索结果-内蒙古大学图书馆

Multi-modal Remote Sensing Image Registration via Modality Perception and Self-Supervised Position Estimation

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Xiao, Yun Zhang, Chunlei Jiang, Bo Chen, Yuan Tang, Jin Anhui University Key Laboratory of Intelligent Computing & Signal Processing (Anhui University) Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Hefei 230601 China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei 230601 China Anhui University School of Internet Hefei 230601 China

Multi-modal remote sensing images registration ensures that images from different sensors or modalities are spatial and informational consistent for effective comparison and analysis. However, due to the non-linear modality gaps that exist between images, making it difficult to focus only on the spatial position differences of the images and ignore the modality gaps. In this paper, to address this issue, we propose a new framework for Multi-Modal remote sensing image Registration, named MMRNet. The proposed framework comprises the following main aspects. First, a novel self-supervised Positional Misalignment Estimator (PME) is designed for multi-modal image registration. PME is able to efficiently overcome the modality gaps and learn the positional differences between multi-modal images more reliably, optimizing the registration loss by minimizing the positional differences directly. Then, a new paradigm of modality translation, termed Modality Perception Module (MPM), is introduced to effectively learn modality gaps and perform modality translation in the case of positional misalignment. Finally, we further design the modality perception guidance loss to supervise the modality translation task, which can encourage the fidelity of the generated pseudo-modality images. Our registration network integrates both rigid registration model and non-rigid registration model. Experimental results demonstrate that the proposed registration framework can obtain obviously superior performance in both rigid and non-rigid image registration tasks on optical-SAR data, optical-map data and optical-infrared data. © 1980-2012 IEEE.

关键词： image registration modality translation Multi-modal learning remote sensing processing rigid and non-rigid transformation

来源：评论

学校读者我要写书评

暂无评论

Group-wise inhibition based feature regularization for robust classification

arXiv

引用

arXiv 2021年

作者： Liu, Haozhe Wu, Haoqian Xie, Weicheng Liu, Feng Shen, Linlin 1Computer Vision Institute College of Computer Science and Software Engineering 2SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society 3National Engineering Laboratory for Big Data System Computing Technology 4Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen 518060 China

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://***/LinusWu/TENET_Training. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-regulated learning for egocentric video activity anticipation

arXiv

引用

arXiv 2021年

作者： Qi, Zhaobo Wang, Shuhui Su, Chi Su, Li Huang, Qingming Tian, Qi The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Kingsoft Cloud Beijing100085 China Cloud BU Huawei Technologies Shenzhen518129 China

Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a simple and effective Self-Regulated Learning framework, which aims to regulate the intermediate representation consecutively to produce representation that (a) emphasizes the novel information in the frame of the current time-stamp in contrast to previously observed content, and (b) reflects its correlation with previously observed frames. The former is achieved by minimizing a contrastive loss, and the latter can be achieved by a dynamic reweighing mechanism to attend to informative frames in the observed content with a similarity comparison between feature of the current frame and observed frames. The learned final video representation can be further enhanced by multi-task learning which performs joint feature learning on the target activity labels and the automatically detected action and object class tokens. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets. Its effectiveness is also verified by the experimental fact that the action and object concepts that support the activity semantics can be accurately identified. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multilevel Characteristic Basis Function Method with ACA for Accelerated Solution of Electrically Large Scattering Problems

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2018年第3期35卷 449-454页

作者： Li Chenlu Sun Yufa Wang Zhonggen Wang Guohua Key Laboratory of Intelligent Computing & Signal Processing Ministry of EducationAnhui University College of Electrical and Information Engineering Anhui University of Science and Technology

The multilevel characteristic basis function method(MLCBFM)with the adaptive cross approximation(ACA)algorithm for accelerated solution of electrically large scattering problems is studied in this *** the conventional MLCBFM based on Foldy-Lax multiple scattering equations,the improvement is only made in the generation of characteristic basis functions(CBFs).However,it does not provide a change in impedance matrix filling and reducing matrix calculation procedure,which is *** reality,all the impedance and reduced matrix of each level of the MLCBFM have low-rank property and can be calculated ***,ACA is used for the efficient generation of two-level CBFs and the fast calculation of reduced matrix in this *** results are given to demonstrate the accuracy and efficiency of the method.

关键词： multilevel characteristic basis function method(MLCBFM) adaptive cross approximation(ACA) characteristic basis functions(CBFs) electromagnetic scattering

来源：评论

学校读者我要写书评

暂无评论

Poisoning attack against estimating from pairwise comparisons

arXiv

引用

arXiv 2021年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Big Data Mining and Knowledge Management The School of Economics and Management University of Chinese Academy of Sciences Beijing100049 China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically. © 2021, CC BY-NC-ND.

关键词： Toys

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of individual core-shell-structured Sn O2@C nanofibers investigated by atomic force microscopy and finite element method

引用

science China(Technological sciences) 2018年第8期61卷 1144-1149页

作者： LIU Xing LI KeFeng DUAN XiaoLu HUANG YuTing LI Shuai LIU YiLin XU Fu LI Zheng ZHANG Ping DING YanHuai Institute of Rheological Mechanics Xiangtan University School of Science Harbin Institute of Technology at Shenzhen Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University

Although SnO_2-based nanomaterials used to be considered as being extraordinarily versatile for application to nanosensors,microelectronic devices, lithium-ion batteries, supercapacitors and other devices, the functionalities of SnO_2-based nanomaterials are severely limited by their intrinsic vulnerabilities. Facile electrospinning was used to prepare SnO_2 nanofibers coated with a protective carbon layer. The mechanical properties of individual core-shell-structured SnO_2@C nanofibers were investigated by atomic force microscopy and the finite element method. The elastic moduli of the carbon-coated SnO_2 nanofibers remarkably increased, suggesting that coating SnO_2 nanofibers with carbon could be an effective method of improving their mechanical properties.

关键词： SnO2 nanofiber core-shell structure elastic modulus atomic force microscopy finite element method

来源：评论

学校读者我要写书评

暂无评论

DHMM-Based Asynchronous Finite-Time Sliding Mode Control for Markovian Jumping Lur’e Systems

Research Square

引用

Research Square 2021年

作者： Nie, Rong Du, Wenli Li, Zhongmei Zhou, Zhao He, Shuping Key Laboratory of Smart Manufacturing in Energy Chemical Process East China University of Science and Technology Ministry of Education Shanghai200237 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China

This paper is concerned with the asynchronous problem for a class of Markovian jumping Lur’s system (MJLSs) via sliding mode control (SMC) in continuous-time domain. Specifically, the discrete hidden Markovian model (DHMM) is employed to describe the nonsynchronization between the controller modes and the MJLSs modes. In particular, considering the nonlinearity of MJLSs, a novel Lur’e-integral-type sliding surface is constructed. In order to ensure the finite-time stability of sliding mode dynamics and the accessibility of the specified sliding surface, the asynchronous Lur’e-type SMC law of the detector mode is presented. Finally, an example of DC motor is provided to demonstrate the effectiveness of the proposed technique. © 2021, CC BY.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Optimizing Two-way Partial AUC with an End-to-end Framework

arXiv

引用

arXiv 2022年

作者： Yang, Zhiyong Xu, Qianqian Bao, Shilong He, Yuan Cao, Xiaochun Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Security Department of Alibaba Group Hangzhou311121 China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Shenzhen518107 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

The Area Under the ROC Curve (AUC) is a crucial metric for machine learning, which evaluates the average performance over all possible True Positive Rates (TPRs) and False Positive Rates (FPRs). Based on the knowledge that a skillful classifier should simultaneously embrace a high TPR and a low FPR, we turn to study a more general variant called Two-way Partial AUC (TPAUC), where only the region with TPR ≥ α, FPR ≤ β is included in the area. Moreover, a recent work shows that the TPAUC is essentially inconsistent with the existing Partial AUC metrics where only the FPR range is restricted, opening a new problem to seek solutions to leverage high TPAUC. Motivated by this, we present the first trial in this paper to optimize this new metric. The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss. To address this issue, we propose a generic framework to construct surrogate optimization problems, which supports efficient end-to-end training with deep learning. Moreover, our theoretical analyses show that: 1) the objective function of the surrogate problems will achieve an upper bound of the original problem under mild conditions, and 2) optimizing the surrogate problems leads to good generalization performance in terms of TPAUC with a high probability. Finally, empirical studies over several benchmark datasets speak to the efficacy of our framework. © 2022, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

LogoDet-3K: A large-scale image dataset for logo detection

arXiv

引用

arXiv 2020年

作者： Wang, Jing Min, Weiqing Hou, Sujuan Ma, Shengnan Zheng, Yuanjie Jiang, Shuqiang School of Information Science and Engineering Shandong Normal University Shandong250358 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Logo detection has been gaining considerable attention because of its wide range of applications in the multimedia field, such as copyright infringement detection, brand visibility monitoring, and product brand management on social media. In this paper, we introduce LogoDet-3K, the largest logo detection dataset with full annotation, which has 3,000 logo categories, about 200,000 manually annotated logo objects and 158,652 images. LogoDet-3K creates a more challenging benchmark for logo detection, for its higher comprehensive coverage and wider variety in both logo categories and annotated objects compared with existing datasets. We describe the collection and annotation process of our dataset, analyze its scale and diversity in comparison to other datasets for logo detection. We further propose a strong baseline method Logo-Yolo, which incorporates Focal loss and CIoU loss into the state-of-the-art YOLOv3 framework for large-scale logo detection. Logo-Yolo can solve the problems of multi-scale objects, logo sample imbalance and inconsistent bounding-box regression. It obtains about 4% improvement on the average performance compared with YOLOv3, and greater improvements compared with reported several deep detection models on LogoDet-3K. The evaluations on other three existing datasets further verify the effectiveness of our method, and demonstrate better generalization ability of LogoDet-3K on logo detection and retrieval tasks. The LogoDet-3K dataset is used to promote large-scale logo-related research and it can be found at https://***/Wangjing1551/LogoDet-3K-Dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A Genetic Algorithm Based Piecewise Linear Representation of Time Series 14

A Genetic Algorithm Based Piecewise Linear Representation of...

引用

14th IEEE International Conference on intelligent Systems and Knowledge Engineering, ISKE 2019

作者： Yang, Xiyang Zhai, Changxin Li, Fang Liu, Longshu Zhang, Youhua Quanzhou Normal University Key Laboratory of Intelligent Computing and Information Processing of Fujian Province Quanzhou China Quanzhou Normal University School of Mathematics and Computer Science Quanzhou China Beijing Normal University School of Mathematical Science Beijing China

ISBN: (纸本)9781728123486

Line Segment Representation (LSR) refers to represents a time series by a few of line segments, such that the original time series and the piecewise line segment series have shapes as similar as possible. Because of its simple expression, LSR based time series are often easier to be understood and computed for some time series datamining tasks than the original raw data. Two kinds of continuous LSR methods, namely, 11 trend filtering and mix-integer programming (MILP) method, are discussed in this paper. To overcome the poor representation ability of l1 trend filtering, and the high computational complexity of MILP, this paper proposes a hybrid method combining GA and linear programming (GA-LP) to find the optimal LSR time series efficiently. In GA-LP, locations of the breakpoints of the piecewise linear segment are fixed by GA, and values on these locations are fixed by a LP method. Numerical experiments reveal that GA-LP can reduce representation error by comparisons with l1 trend filtering and MILP method, and its computing time is much less than that of MILP. © 2019 IEEE.

关键词： Time series

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：