检索结果-内蒙古大学图书馆

第42届中国控制会议

作者： Youqing Fang Jingwen Jia Yuhai Yang Wan-Li Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui University

CNNs(Convolutional Neural Networks) have a good performance on most classification tasks,but they are vulnerable when meeting adversarial *** and design of highly aggressive adversarial examples can help enhance the security and robustness of *** transferability of adversarial examples is still low in black-box ***,an adversarial example method based on probability histogram equalization,namely HE-MI-FGSM(Histogram Equalization Momentum Iterative Fast Gradient Sign Method) is *** each iteration of the adversarial example generation process,the original input image is randomly histogram equalized,and then the gradient is calculated to generate adversarial perturbations to mitigate overfitting in the adversarial *** effectiveness of the method is verified on the ImageNet *** with the advanced method I-FGSM(Iterative Fast Gradient Sign Method) and MI-FGSM(Momentum I-FGSM),the attack success rate in the adversarial training network increased by 27.9% and 7.7% on average,respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Capacity Reversible Data Hiding Scheme based on Interpolation and Tetris Matrix

High Capacity Reversible Data Hiding Scheme based on Interpo...

引用

第41届中国控制会议

作者： Fei-Fei Qian Nuo Xu Wan-Li Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Interpolation technology has evolved into a powerful tool for reversible data hiding in the image processing ***,existing interpolated algorithms only have a trivial impact on image *** this paper,an innovative interpolation and matrix-based algorithm is proposed.A novel concept of the difference between interpolated pixels is represented to dramatically improve the visual quality of the image,which lays a solid foundation for the subsequent data hiding *** is growing evidence that the Tetris matrix plays a vital role in improving embedding *** is worth mentioning that our scheme can intensely resist different attacks of various *** experimental findings demonstrate that the effect of our proposed scheme is unprecedentedly perfect even though a higher capacity is embedded than with traditional steganography approaches.

关键词： Data hiding interpolation image processing

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability Reversible Adversarial Examples Based on Flipping Transformation

Improving Transferability Reversible Adversarial Examples Ba...

引用

作者： Youqing Fang Jingwen Jia Yuhai Yang Wanli Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University

Adding subtle perturbations to an image can cause the classification model to misclassify, and such images are called adversarial examples. Adversarial examples threaten the safe use of deep neural networks, but when combined with reversible data hiding(RDH) technology, they can protect images from being correctly identified by unauthorized models and recover the image lossless under authorized models. Based on this, the reversible adversarial example(RAE) is rising. However, existing RAE technology focuses on feasibility, attack success rate and image quality, but ignores transferability and time complexity. In this paper,we optimize the data hiding structure and combine data augmentation technology,which flips the input image in probability to avoid overfitting phenomenon on the dataset. On the premise of maintaining a high success rate of white-box attacks and the image's visual quality, the proposed method improves the transferability of reversible adversarial examples by approximately 16% and reduces the computational cost by approximately 43% compared to the state-of-the-art method. In addition, the appropriate flip probability can be selected for different application scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Membrane Algorithms on GPU

An Implementation of Membrane Algorithms on GPU

引用

The Second Asian Conference on Membrane computing(ACMC2013)

作者： Xingyi Zhang Dong Qin Zhuanlian Ding Jin Tang Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University

Membrane algorithms are a new class of heuristic algorithms, which attempt to incorporate some components of membrane computing models (also called P systems) for designing efficient optimization algorithms, such as the structure of P systems, the way of communication between cells, etc. Membrane algorithms are a kind of parallel methods, where many operations can be performed in parallel. Although the importance of the parallelism of such algorithms is recognized, membrane algorithms were often implemented on the serial computing device Central processing Unit (CPU), which makes the algorithms cannot work in a more efficient way. In this work, we consider the implementation of membrane algorithms on the parallel computing device Graphics processing Unit (GPU). Under such implementation, all cells of membrane algorithms can work simultaneously. Experiment results on two classical intractable problems, point set matching problem and TSP, show that GPU implementation of membrane algorithms is much more efficient than CPU implementation in terms of runtime, especially for solving the problems with a high complexity.

关键词： Membrane computing Membrane algorithm Parallel computing device GPU

来源：评论

学校读者我要写书评

暂无评论

Parametric local multimodal hashing for cross-view similarity search

Parametric local multimodal hashing for cross-view similarit...

引用

23rd International Joint Conference on Artificial Intelligence, IJCAI 2013

作者： Zhai, Deming Chang, Hong Zhen, Yi Liu, Xianming Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology Harbin China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9781577356332

Recent years have witnessed the growing popularity of hashing for efficient large-scale similarity search. It has been shown that the hashing quality could be boosted by hash function learning (HFL). In this paper, we study HFL in the context of multimodal data for cross-view similarity search. We present a novel multimodal HFL method, called Parametric Local Multimodal Hashing (PLMH), which learns a set of hash functions to locally adapt to the data structure of each modality. To balance locality and computational efficiency, the hashing projection matrix of each instance is parameterized, with guaranteed approximation error bound, as a linear combination of basis hashing projections of a small set of anchor points. A local optimal conjugate gradient algorithm is designed to learn the hash functions for each bit, and the overall hash codes are learned in a sequential manner to progressively minimize the bias. Experimental evaluations on cross-media retrieval tasks demonstrate that PLMH performs competitively against the state-of-the-art methods.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Compressive Sensing for Wide-Angle Analysis

Compressive Sensing for Wide-Angle Analysis

引用

第九届国际天线、电波传播及电磁理论学术研讨会(ISAPE2010)

作者： Hong-Mei Du Yi-Cai Mei Si-Long Lu Ming-Sheng Chen Xian-Liang Wu Key Lab of Intelligent Computing & Signal Processing Anhui University Ministry of Education Hefei Department of Physics and Electronic Engineering Hefei Normal University Hefei 230601 China Schoo Key Lab of Intelligent Computing & Signal Processing Anhui University Ministry of Education Hefei

A new incident source with different angles was constructed for dealing with wide-angle scattering problems. Considering the impendence matrix in method of moments (MOM） is independent from incident angles, the equivalent relationship between induced current and the measured CS-current was build, while the CS-current can be computed directly under the new incident source. Finally, we can reconstruct the induce current by utilizing the theory of compressive sensing (CS). Compared with traditional MOM, the computational complexity can be greatly reduced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pushing scientific documents by discovering interest in information flow within E-science knowledge grid

引用

4th International Conference on Grid and Cooperative computing - GCC 2005

作者： Ding, Lianhong Li, Xiang Xing, Yunpeng Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Graduate School of Chinese Academy of Sciences 100080 Beijing China Hunan Knowledge Grid Lab. Hunan University of Science and Technology Hunan China

ISBN: (纸本)3540305106

The Knowledge Grid is an intelligent and sustainable Internet application environment that enables people and roles to effectively capture, publish, share and manage explicit knowledge resources. As an important function of the e-Science Knowledge Grid, this paper proposes an approach to effectively push scientific documents within research teams by detecting the social characteristics in self-organized network, discovering interest in information flow, and capturing dynamic changes of interests over time. The proposed approach can be used in any cooperative organizations. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Information analysis

来源：评论

学校读者我要写书评

暂无评论

Structural holes study of ICML collab.rative network

引用

Journal of Computational Information Systems 2014年第24期10卷 10715-10722页

作者： Duan, Weiwei Qian, Fulan Shi, Lei Zhang, Yanping School of Computer Science and Technology Anhui University Hefei China Key Lab of Intelligent Computing and Signal Processing Anhui University Hefei China

Collab.ration among authors is a pervasive phenomenon currently. Mining useful information from cooperation is a significant study to unravel relationships underneath these papers and predict potential collab.rations or future popular academic topics. This paper demonstrates the change of Structural Holes in the whole network and for some individual authors from 2009 to 2012 in ICML. This paper is going to study the biggest subset in 2009, which separates into several smaller subsets with less structural holes in 2010 and 2011, while the number of structural holes in 2012 increases. The graphs of the whole networks from 2009 to 2012 drawn by Ucinet are going to demonstrate the changes of structural holes from 2009 to 2012 and expl the reason why there are more structural holes in 2012 compared to 2010 and 2011. The reason is that the ainnumber of authors in 2012 increases about 50 percent compared to 2011, which results in that authors need to find new collab.rations and leaders may become intermediaries to connect new authors and existing authors occupying structural holes. And some authors whose papers are published on ICML continuously from 2009 to 2012 are going to be analysed to indicate the changes of their position in the network. Some authors are increasingly constrained in certain groups, while some other authors become bridges connecting different groups and some other authors changes are correspond to the changes of the whole network. They are constrained in certain subset with less structural holes in 2010 and 2011 but, due to large number of authors joining in ICML, more likely to occupy more structural holes.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Collab.rating semantic link network with resource space model

引用

4th International Conference on Grid and Cooperative computing - GCC 2005

作者： Xing, Yunpeng Liu, Jie Sun, Xiaoping Yao, Erlin Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate School Chinese Academy of Sciences Beijing China Hunan Knowledge Grid Lab. Hunan University of Science and Technology Hunan China

ISBN: (纸本)3540305106

The Semantic Link Network model SLN and Resource Space Model RSM are semantic models proposed separately for effectively specifying and managing versatile resources across the Internet. Collab.rating the relational semantics of SLN with the classification semantics of the RSM can support richer semantic modeling in applications. This paper introduces the Resource Class Hierarchies into the SLN and investigates to cooperatively model with the RSM. The proposed approach can be used as a normalized semantic overlay of the Knowledge Grid environment. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Adaptively feature matching via joint transformational-spatial clustering

Adaptively feature matching via joint transformational-spati...

引用

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

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：