检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Wei, Kangkang Luo, Weiqi Tan, Shunquan Huang, Jiwu The Guangdong Key Lab of Information Security Technology School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Up to now, most existing steganalytic methods are designed for grayscale images, and they are not suitable for color images that are widely used in current social networks. In this paper, we design a universal color image steganalysis network (called UCNet) in spatial and JPEG domains. The proposed method includes preprocessing, convolutional, and classification modules. To preserve the steganographic artifacts in each color channel, in preprocessing module, we firstly separate the input image into three channels according to the corresponding embedding spaces (i.e. RGB for spatial steganography and YCbCr for JPEG steganography), and then extract the image residuals with 62 fixed high-pass filters, finally concatenate all truncated residuals for subsequent analysis rather than adding them together with normal convolution like existing CNN-based steganalyzers. To accelerate the network convergence and effectively reduce the number of parameters, in convolutional module, we carefully design three types of layers with different shortcut connections and group convolution structures to further learn high-level steganalytic features. In classification module, we employ a global average pooling and fully connected layer for classification. We conduct extensive experiments on ALASKA II to demonstrate that the proposed method can achieve state-of-the-art results compared with the modern CNN-based steganalyzers (e.g., SRNet and J-YeNet) in both spatial and JPEG domains, while keeping relatively few memory requirements and training time. Furthermore, we also provide necessary descriptions and many ablation experiments to verify the rationality of the network design. Copyright © 2021, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Xiao, Zhiqing Wang, Haobo Jin, Ying Feng, Lei Chen, Gang Huang, Fei Zhao, Junbo College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University China CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore Alibaba Group China

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces;(ii)-we further develop a fine-grained message propagation module — upon a novel neighbor-aware self-training mechanism — in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://***/CrownX/SPA. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

SoLar: Sinkhorn label Refinery for Imbalanced Partial-label Learning

arXiv

引用

arXiv 2022年

作者： Wang, Haobo Xia, Mingxuan Li, Yixuan Mao, Yuren Feng, Lei Chen, Gang Zhao, Junbo Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University China School of Software Technology Zhejiang University China Department of Computer Sciences University of Wisconsin-Madison United States College of Computer Science Chongqing University China Center for Advanced Intelligence Project RIKEN Japan

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior work failed. We subsequently propose SoLar, a novel Optimal Transport-based framework that allows to refine the disambiguated labels towards matching the marginal class prior distribution. SoLar additionally incorporates a new and systematic mechanism for estimating the long-tailed class prior distribution under the PLL setup. Through extensive experiments, SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-of-the-art PLL methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Taxi Demand Prediction with LSTM-Based Combination Model

Taxi Demand Prediction with LSTM-Based Combination Model

引用

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Yongxuan Lai Kaixin Zhang Junqiang Lin Fan Yang Yi Fan Shenzhen Research Institute Xiamen University Shenzhen China School of Informatics Xiamen University Xiamen China Department of Automation Xiamen University Xiamen China School of Mathematics and Statistics Key Laboratory of Complex Systems and Intelligent Computing Qiannan Normal University for Nationalities Duyun China Guangxi Key Lab of Trusted Software Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Taxi demands to predict in urban city helps to guide the drivers to cruise and pickup riders, which increases drivers' income and decreases riders' waiting time. The taxi demands prediction problem is usually cast as a time series prediction task, and deep models such as recurrent neural network (RNN) or long short-term memory (LSTM) is adopted for the prediction. In this paper, we present a LSTM-based combination model to predict taxi demand based on the recent demand and other relevant information. More specifically, we use a spatio-temporal component to capture the spatio-temporal information and use an attribute component to obtain external information (e.g. weather, point of interest), and these two components are combined to make the final predictions. We evaluate our method of two real-world datasets, and the results show that the proposed approach outperforms other prediction methods.

关键词： Public transportation Urban areas Predictive models Time series analysis Meteorology Autoregressive processes Data models

来源：评论

学校读者我要写书评

暂无评论

Active self-paced learning for cost-effective and progressive face identification

arXiv

引用

arXiv 2017年

作者： Lin, Liang Wang, Keze Meng, Deyu Zuo, Wangmeng Zhang, Lei School of Data and Computer Science Sun Yat-sen University Guangzhou China Engineering Research Center Advanced Computing Engineering Software of Ministry of Education China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi'an Jiaotong University China School of Computer Science and Technology Harbin Institute of Technology Harbin China Dept. of Computing Hong Kong Polytechnic University Hong Kong

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://***/projects/aspl/ Copyright © 201

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Research on fractional order controller based on best rational approximation approach

引用

Journal of Convergence Information technology 2012年第4期7卷 50-58页

作者： Zhao, Huimin Nie, Bing Li, Wen Deng, Wu Software Institute Dalian Jiaotong University Dalian 116028 China Key Laboratory of Numerical Simulation in the Sichuan Provincial College Neijiang Normal University Neijiang 641112 China Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science and Engineering Zigong 643000 China State Key Laboratory of Power Transmission Equipment and System Security and New Technology College of Electrical Engineering Chongqing University Chongqing 400044 China Key Laboratory of advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China

Introduce the basic concept of best rational approximation and constructing procedure of the best rational approximation function in Laplace domain. By an illustrative example the design method of FOC based on best rational approximation is discussed. The performance comparison of transfer functions between the FOC obtained by best rational approximation method and conventional PID shows that it is effective to apply the method in design of FOC, which can guarantee maximum absolute error of amplitude frequency characteristic of approximation function in a given error tolerance.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

arXiv

引用

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

arXiv

引用

arXiv 2024年

作者： Liu, Chanjuan Ge, Shike Chen, Zhihan Pei, Wenbin Zhu, Enqiang Mei, Yi Ishibuchi, Hisao The School of Computer Science and Technology Dalian University of Technology 116024 China The Institute of Software Chinese Academy of Science Beijing100190 China The Institute of Computing Science and Technology Guangzhou University Guangzhou510006 China The School of Engineering and Computer Science Victoria University of Wellington Wellington6012 New Zealand The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledge-guided genetic algorithm is verified by experiments on 26 real-world instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight real-world instances. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Expander Code: A Scalable Erasure-Resilient Code to Keep up with Data Growth in Distributed Storage

Expander Code: A Scalable Erasure-Resilient Code to Keep up ...

引用

IEEE International Performance computing and Communication Conference

作者： Guangping Xu Sheng Lin Hua Zhang Xing Guo Kai Shit Computer and Communication Engineering School Tianjin University of Technology Tianjin China 300384 Tianjin Key Lab. of Intelligence Computing and New Software Technology Tianjin China 300384

ISBN: (纸本)9781479932153

To ensure high reliability and storage efficiency, erasure codes are preferred in storage systems. With the prevalent of distributed storage systems such as clouds storage, how to design a scalable and efficient erasure-resilient code is challenging. We propose a scalable binary linear code to keep up with data growth which has the following properties. Given the group size k and the code block length n, the proposed code corrects any two bit erasures among the n bits. The redundancy overhead of the code is 2/(k + 2), and each data bit affects exactly 2 parity bits. As results of these properties, if a data bit is changed or added, only two parity bits need to be updated;and the recovery of an erasured bit requires accessing at most k other bits and the recovery of two erasured bits requires at most 2k other bits. We give the construction algorithm by the order expansion of regular graphs;moreover, we optimize the failure resilience during the construction procedure. Compared with existing codes, our proposed code has notable benefits in storage scalability, redundancy overhead and I/O bandwidth. The deployment of the proposed code in distributed storage systems can be simple and practical.

关键词： Storage systems Erasure codes Scalability Fault-tolerance Graph expansion

来源：评论

学校读者我要写书评

暂无评论

Research on adaptive strategy for end-hopping system

引用

Tongxin Xuebao/Journal on Communications 2011年第11 A期32卷 51-57页

作者： Zhao, Chun-Lei Jia, Chun-Fu Weng, Chen Lin, Kai College of Information Technical Science Nankai University Tianjin 300071 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300384 China Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin 300384 China

An adaptive strategy was proposed for EH system. Modules of attack detection, feedback transmission and adaptive control were added to original EH system. They could help to make threats analysis and adjust hopping strategy in real time, so as to reduce the probability of the system stepping into the attackers' target area. With the experiments proving the anti-attack ability of the prototype system, the feasibility and effectiveness of adaptive strategy were demonstrated for EH system.

关键词： Network security

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：