检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Chao Qi, Shuren Huang, Zhiqiu Zhang, Yushu Lan, Rushi Cao, Xiaochun Fan, Feng-Lei The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The Department of Mathematics The Chinese University of Hong Kong Hong Kong The Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. However, these decompositions are either biased towards frequency resolution or spatial resolution, thus failing to capture adversarial patterns comprehensively. Also, when the detector relies on few fixed features, it is practical for an adversary to fool the model while evading the detector (i.e., defense-aware attack). Motivated by such facts, we propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition. It expands the above works from two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability, capturing the differences between natural and adversarial data comprehensively in both spatial and frequency distributions, w.r.t. the common trigonometric or wavelet basis;2) the extensive features formed by the Krawtchouk decomposition allows for adaptive feature selection and secrecy mechanism, significantly increasing the difficulty of the defense-aware attack, w.r.t. the detector with few fixed features. Theoretical and numerical analyses demonstrate the uniqueness and usefulness of our detector, exhibiting competitive scores on several deep models and image sets against a variety of adversarial attacks. Copyright © 2023, 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

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

来源：评论

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

Size-invariance matters: rethinking metrics and losses for i...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Retinal Blood Vessel Segmentation by Using Automatic Random Walks Based on Centerline Extraction

引用

BioMed Research International 2020年第0期2020卷 000-000页

作者： Gao, Jianqing Chen, Guannan Lin, Wenru Smart Home Information Collection and Processing on Internet of Things Laboratory of Digital Fujian Fujian Jiangxia University Fuzhou 350108 China School of Electronic Information Science Fujian Jiangxia University Fuzhou 350108 China Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Provincial Key Laboratory for Photonics Technology Fujian Normal University Fuzhou 350007 China Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou 350117 China College of Computer and Control Engineering Minjiang University Fuzhou 350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou 350121 China

The retinal blood vessel analysis has been widely used in the diagnoses of diseases by ophthalmologists. According to the complex morphological characteristics of the blood vessels in normal and abnormal images, an automatic method by using the random walk algorithms based on the centerlines is proposed to segment retinal blood vessels. Hessian-based multiscale vascular enhancement filtering is used to display the vessel structures in maximum intensity projection. Random walk algorithm provides a unique and quality solution, which is robust to weak object boundaries. Seed groups in the random walk segmentation are labeled according to the centerlines, which are extracted by using the divergence of the normalized gradient vector field and the morphological method. Experiments of the proposed method are implemented on the publicly available STARE (the Structured Analysis of the Retina) database. The results are compared to other existing retinal blood vessel segmentation methods with respect to the accuracy, sensitivity, and specificity, and the proposed method is proved to be more sensitive in detecting the retinal blood vessels in both normal and pathological areas. © 2020 Jianqing Gao et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust quantum teleportation via a non-Markovian channel

arXiv

引用

arXiv 2023年

作者： Wang, Yanfang Xue, Shibei Song, Hongbin Jiang, Min Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China General Education Division Shenzhen Key Lab of Semiconductor Lasers The Chinese University of Hong Kong Guang Dong Shenzhen518116 China School of Electronics and Information Engineering Soochow University Suzhou215006 China

In this paper, we propose a non-Markovian quantum channel approach to mitigating the degradation of the average fidelity in continuous-variable quantum teleportation. The non-Markovian quantum channel is modeled by an augmented system, where ancillary systems are introduced to represent the internal modes of non-Markovian environments. With a proper non-Markovianity, enhanced effects of the channels on continuous-variable quantum teleportation are observed. Also, the logarithmic negativity of entangled states can be effectively maintained so that the decay of the average fidelity of quantum teleportation is mitigated. In addition, the analysis on different teleported quantum states shows that coherent states exhibit stronger robustness than those of squeezed states and cat states in quantum teleportation with a non-Markovian channel. Copyright © 2023, The Authors. All rights reserved.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition Embedded Autoencoder

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition ...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Weijia Wang Zhuchang Qi Lue Wang Wei Yang Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Xi'an Institute of Modern Control Technology Xi'an China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Beijing Key Laboratory of Embedded Real-Time Information: Processing Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High-resolution range profile (HRRP) is a crucial technique for radar target recognition. Due to the coupling of azimuthal scattering information and aspect sensitivity, fine target recognition using HRRP remains challenging. One way to mitigate HRRP aspect sensitivity is through enhancing the dimensionality of radar information acquisition. Therefore, this paper proposes a Dual-Band HRRP Fusion Recognition Model via Wavelet Decomposition Embedded Autoencoder (DF-WD-AENet). The method we proposed mainly comprises two modules. Firstly, the autoencoder model based on wavelet decomposition (WD-AEM) achieves constraint on feature information, making it better suited for dual-band fusion. Next is the dual-band information fusion module (DFM), in which we achieved the interaction and fusion of feature information through convolutional block attention module (CBAM) and omni-dimensional dynamic convolution (ODConv), and used a fusion loss function to train the model. Experiment shows that the recognition rate of our method is 7.73% higher than that of single-band, proving the effectiveness of the proposed method.

关键词： Sensitivity Target recognition Convolution Fuses Autoencoders Dual band Scattering Radar Radar signal processing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Alternate control Delayed Systems

Fuzzy Alternate Control Delayed Systems

引用

International Conference on Computer and Communications (ICCC)

作者： Ning Tang Yuming Feng B. O. Onasanya Wei Zhang School of Computer Science and Engineering Chongqing Three Gorges University Wanzhou Chongqing China School of Three Gorges Artificial Intelligence Chongqing Three Gorges University Wanzhou Chongqing China Department of Mathematics University of Ibadan Ibadan Oyo Nigeria Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Chongqing China

This paper studies the asymptotic stability of nonlin-ear systems which is regulated by using fuzzy impulsive control. First of all, the system was formulated, the Lyapunov function was constructed, and then the fuzzy control component required for the nonlinear system to exhibit global asymptotic exponential stability under the regulation of the impulsive controller was developed. A unique fuzzy concept was introduced herein, which, compared to the conventional precise counterpart, was defined to perform only scalar approximations. Subsequently, a set of conditions sufficient for global asymptotic exponential stability was proposed for the impulsive controller. Halany inequality and its key generalizations were used while working out the mathematical proofs. Finally, examples were given to verify the general results obtained and their applicability.

关键词： Fuzzy control Protocols Stability control systems Regulation Delays control theory

来源：评论

学校读者我要写书评

暂无评论

An Insight Into Neurodegeneration: Harnessing Functional MRI Connectivity in the Diagnosis of Mild Cognitive Impairment

An Insight Into Neurodegeneration: Harnessing Functional MRI...

引用

17th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2024

作者： Han, Shuning Sun, Zhe Zhao, Kanhao Duan, Feng Caiafa, Cesar F. Zhang, Yu Solé-Casals, Jordi Data and Signal Processing Research Group University of Vic-Central University of Catalonia Catalonia Vic08500 Spain Image Processing Research Group RIKEN Center for Advanced Photonics Riken Saitama Wako-Shi Japan Faculty of Health Data Science Juntendo University Chiba Urayasu Japan Department of Bioengineering Lehigh University BethlehemPA18015 United States Tianjin Key Laboratory of Brain Science and Intelligent Rehabilitation Nankai University Tianjin China Instituto Argentino de Radioastronomía-CCT La Plata CONICET/ CIC-PBA/ UNLP V. Elisa 1894 Argentina Department of Electrical and Computer Engineering Lehigh University BethlehemPA18015 United States Department of Psychiatry University of Cambridge CambridgeCB20SZ United Kingdom

Alzheimer’s disease is a progressive form of memory loss that worsens over time. Detecting it early, when memory issues are mild, is crucial for effective interventions. Recent advancements in computer technology, specifically Graph Convolutional Networks (GCNs), have proven to be powerful tools for analyzing Magnetic Resonance Imaging (MRI) data comprehensively. In this study, we developed a GCN framework for diagnosing mild cognitive impairment (MCI) by examining the functional connectivity (FC) derived from resting-state functional MRI (rfMRI) data. Our research systematically explored various types and processing methods of FC, evaluating their performance on the OASIS-3 dataset. The experimental results revealed several key findings. On the one hand, the proposed GCN exhibited significantly superior performance over both the baseline GCN and the Support Vector Machine (SVM) models, with statistically significant differences. It attained the highest average accuracy of 80.3% and a peak accuracy of 88.2%. On the other hand, the GCN frame work obtained using individual FCs showed overall slightly better performance than the one using global FCs. However, it is important to note that GCNs using global networks with appropriate connectivity can achieve comparable or even better performance than individual networks in certain cases. Finally, our results also indicate that the connectivity within specific brain regions, such as VIS, DMN, SMN, VAN, and FPC, may play a more significant role in GCN-based MRI classification for MCI diagnosis. These findings significantly contribute to the understanding of neurodegenerative disorders and offer valuable insights into the diverse ap plications of GCNs in brain analysis and disease detection. © 2024 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Recognition via Wavelet Packet Decomposition and Redundancy Reduction Model

Dual-Band HRRP Recognition via Wavelet Packet Decomposition ...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Wei Yang Zhuchang Qi Heke Wu Yang Li Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China Xi'an Institute of Modern Control Technology Xi’an China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Beijing Key Laboratory of Embedded Real-Time Information: Processing Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High resolution range profiles (HRRP) is widely used in radar automatic target recognition. Due to aspect sensitivity, HRRP of different targets can be similar under certain aspects, making it difficult for recognition via traditional methods. One way to mitigate it is to increase the frequency dimension, utilizing the differences of target frequency response to extract inter-class discriminative information. Therefore, we propose a HRRP recognition model based on redundancy reduction criterion and wavelet packet decomposition. Specifically, we use deep wavelet packet decomposition to perform multi-level decomposition of dual-band HRRP and adaptively extract discriminative features of sub-wavelets; we use redundancy reduction layer to cluster intra-class features and expand inter-class features, thereby reducing feature heterogeneity. Furthermore, we propose a deep discriminative correlation analysis for joint analysis and transformation of dual-band features to fuse complementary information. Experimental results show that proposed method has excellent recognition performance. Additionally, analysis study also verify the effectiveness of each submodule.

关键词： Sensitivity Limiting Target recognition Fuses Redundancy Dual band Radar Feature extraction Wavelet packets Frequency response

来源：评论

学校读者我要写书评

暂无评论

Unequal Error Protection Rateless Codes for Spatial Audio Transmission

Unequal Error Protection Rateless Codes for Spatial Audio Tr...

引用

International Conference on Communication Technology (ICCT)

作者： Junpeng Yin Yusun Fu Haobo Huang Jinhui Tang Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

Spatial audio is an important component of the metaverse. With the rapid increase of the spatial resolution and the number of objects, the data volume of the spatial side information has grown larger. However, the low bit rate transmission of spatial side information in the object-based audio coding methods leads to the low-quality reconstruction of spatial side information with limited bandwidth. To address this issue, this paper constructs a cascade design of spatial audio coding and unequal error protection (UEP) rateless codes. Furthermore, the further protection of specific spatial side information is proposed for different scenarios, which effectively addresses the limitation of traditional spatial audio coding in side information protection. For the situation where the code length K of different importance levels is different, we propose an adaptive degree distribution (ADD), adding K to the selection probability as an influencing factor, which has better performance than other degree distribution for short code length. ADD is used to replace the multiple degree distribution strategy of the traditional unequal error protection scheme, and the block error rate (BER) is reduced nearly 10 times compared with the traditional scheme.

关键词： Codes Error analysis Metaverse Distribution strategy Spatial audio Bit rate Symbols Communications technology Protection Spatial resolution

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：