检索结果-内蒙古大学图书馆

Dual-stream network with complementary fusion and hierarchical attention for image tampering localization

signal image AND VIDEO processing 2025年第3期19卷 1-14页

作者： Mao, Zhanpeng Lu, Tongwei Wuhan Inst Technol Sch Comp Sci & Engn Wuhan 430205 Hubei Peoples R China Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430205 Hubei Peoples R China

In recent years, with the rapid development of image editing technology, the trustworthiness of multimedia data is facing severe challenges, and the security risks caused by image tampering are increasing, which promotes the research of image tampering localization. Traditional image tampering localization methods usually rely on identifying specific forgery traces, such as JPEG artifacts, edge inconsistencies, camera noise, and so on, and localize the tampered regions by cross-entropy loss. With the rise of deep learning, recent studies explore the boundary difference between tampered regions and real regions by adding Convolutional neural Network and attention mechanism. However, there are two main weaknesses in these methods. First, the existing two-stream networks lack complementary fusion between blocks, and the features of the two branches lack interaction. The second is that they tend to focus on only a few specific forgery artifacts. In fact, the tampered images in real life may be generated by a variety of forgery methods, leaving a variety of tampering traces. To solve these problems, this paper proposes a novel image tampering Location network based on dual-stream dominant multi-step complementary fusion feature and multi-scale attention enhancement feature representation. The network combines the RGB feature and noise feature of the image to accurately identify and locate the possible tampering traces in the image. Specifically, our proposed RGB-Noise Complementary Fusion Module uses the weighting mechanism to complementary correct RGB features and Noise features, and fuses features to compensate for the lack of single-stream information while highlighting important features. In addition, Hierarchical Attention Module processes features at four scales at multiple levels, enabling the network to capture not only local details, but also global structural information, helping the model more accurately locate tampering regions. Experimental results show that

关键词： image editing Tamper localization Dual-stream encoder-decoder network RGB-noise complementary fusion module Hierarchical attention module

来源：评论

学校读者我要写书评

暂无评论

Bayesian Deep Learning via Expectation Maximization and Turbo Deep Approximate Message Passing

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 3865-3878页

作者： Xu, Wei Liu, An Zhang, Yiting Lau, Vincent Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Hong Kong Univ Sci & Technol Dept ECE Hong Kong Peoples R China

Efficient learning and model compression algorithm for deep neural network (DNN) is a key workhorse behind the rise of deep learning (DL). In this work, we propose a message passing-based Bayesian deep learning algorithm called EM-TDAMP to avoid the drawbacks of traditional stochastic gradient descent (SGD)-based learning algorithms and regularization-based model compression methods. Specifically, we formulate the problem of DNN learning and compression as a sparse Bayesian inference problem, in which group sparse prior is employed to achieve structured model compression. Then, we propose an expectation maximization (EM) framework to estimate posterior distributions for parameters (E-step) and update hyperparameters (M-step), where the E-step is realized by a newly proposed turbo deep approximate message passing (TDAMP) algorithm. We further extend the EM-TDAMP and propose a novel Bayesian federated learning framework, in which the clients perform TDAMP to efficiently calculate the local posterior distributions based on the local data, and the central server first aggregates the local posterior distributions to update the global posterior distributions and then update hyperparameters based on EM to accelerate convergence. We detail the application of EM-TDAMP to Boston housing price prediction and handwriting recognition, and present extensive numerical results to demonstrate the advantages of EM-TDAMP.

关键词： Bayes methods Training Deep learning signal processing algorithms Message passing Federated learning Neurons Bayesian deep learning Bayesian federated learning DNN model compression expectation maximization turbo deep approximate message passing

来源：评论

学校读者我要写书评

暂无评论

A Weak Anomaly signal Enhancement Method Based on Vector Magnetic Sensor

引用

IEEE Sensors Journal 2025年第12期25卷 22479-22487页

作者： Sun, Hexuan Qiu, Jing Huang, Shuanglong Zeng, Xinjie Cao, Cong Liu, Libo Chongqing University Key Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China College of Optoelectronic Engineering Chongqing400044 China

In complex magnetic field detection scenarios, magnetic anomaly detection signals are often submerged in environmental magnetic noise and are difficult to identify. A new method for enhancing weak anomaly signals based on vector magnetic sensors is proposed. The new method uses a stochastic resonance system based on an exponential potential function to process preprocessed vector magnetic signals. Then, the enhancement factor of magnetic anomaly signals is calculated based on the stochastic resonance processing results of vector signals. Finally, by combining the signal enhancement factor with the preprocessed total field signal, the proposed method effectively suppresses background noise, amplifies weak magnetic anomaly signals, and enhances detection reliability. Simulations and experiments show that the proposed method exhibits excellent performance under various noise backgrounds. Compared with the original real signal with a signal-to-noise ratio of -15dB, the signal-to-noise ratio of this proposed method is improved by 16.5dB, and is superior to many typical methods for processing magnetic anomaly signals. In addition, the proposed method has achieved good results in field tests of magnetic anomaly measurement, effectively processing and enhancing magnetic anomalies in low signal-to-noise ratio acquisition signals. © 2001-2012 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Expressivity of Hidden Markov Chains vs. Recurrent neural Networks From a System Theoretic Viewpoint

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 4178-4191页

作者： Desbouvries, Francois Petetin, Yohan Salaun, Achille Inst Polytech Paris Samovar Telecom SudParis F-91120 Palaiseau France Nokia Bell Labs Nozay France Univ Oxford Inst Biomed Engn Dept Engn Sci Oxford OX3 7DQ England

Hidden Markov Chains (HMC) and Recurrent neural Networks (RNN) are two well known tools for predicting time series. Even though these solutions were developed independently in distinct communities, they share some similarities when considered as probabilistic structures. So in this paper we first consider HMC and RNN as generative models, and we embed both structures in a common generative unified model (GUM). We next address a comparative study of the expressivity (or modeling power) of these models, which here refers to the range of the joint probability distribution of an observations sequence, induced by the underlying latent variables. To that end we assume that the models are furthermore linear and Gaussian. The probability distributions produced by these models are characterized by structured covariance series, and as a consequence expressivity reduces to comparing sets of structured covariance series, which enables us to call for stochastic realization theory (SRT). We finally provide conditions under which a given covariance series can be realized by a GUM, an HMC or an RNN.

关键词： Hidden Markov models Computational modeling Time series analysis Buildings Bayes methods Recurrent neural networks Predictive models Hidden Markov Chains Recurrent neural Networks generative models expressivity modeling power stochastic realization theory

来源：评论

学校读者我要写书评

暂无评论

Direct sequence spread spectrum (DSSS) signal detection based on eigenvalues local binary pattern residual network (EL-ResNet)

引用

signal image AND VIDEO processing 2024年第5期18卷 4741-4751页

作者： Wang, Bo Shen, Lei Wang, Huaxia Yao, Yudong Hangzhou Dianzi Univ Coll Commun Engn Hangzhou 310018 Zhejiang Peoples R China Oklahoma State Univ Coll Engn Architecture & Technol CEAT Stillwater OK 74078 USA Stevens Inst Technol Hoboken NJ 07030 USA

Direct sequence spread spectrum (DSSS) communications are highly significant in military and civilian wireless communications because of its ability to resist narrowband interference, multipath interference and high security. However, under low signal-to-noise ratio (SNR), the detection of DSSS signals becomes very difficult under non-cooperative communication. Therefore, in order to improve the detection performance of DSSS signals in fading channels with low SNR, a DSSS signal detection method based on an eigenvalues local binary patterns residual network (EL-ResNet) is proposed with an unknown spread spectrum sequence. Firstly, according to the characteristics of DSSS signals, the eigenvalues of the sample covariance matrix of the DSSS signals are used to construct the signal eigenvalue histograms. This method uses the strong contrast of eigenvalue energy and gradient change to enlarge the discrimination of images with or without DSSS signals. Then, EL-ResNet is built to distinguish between eigenvalue histograms with or without DSSS signals. The local binary patterns (LBPs) are introduced to constrain the loss function of the network, increasing the differentiation of the two types of eigenvalue histograms, and improving the DSSS signal detection performance of the network. Finally, the experimental results show that the performance of the DSSS signal detection method based on EL-ResNet is larger than fast Fourier transform (FFT), FFT-deep neural network (FFT-DNN), covariance matrix-convolutional neural network (CM-CNN) detection methods.

关键词： DSSS signals detection signal eigenvalue histograms EL-ResNet

来源：评论

学校读者我要写书评

暂无评论

Adaptive data-driven subsampling for efficient neural network inference

引用

signal image AND VIDEO processing 2024年第6-7期18卷 5163-5171页

作者： Machidon, Alina L. Pejovic, Veljko Univ Ljubljana Fac Comp & Informat Sci Vecna Pot 113 Ljubljana 1000 Slovenia Inst Jozef Stefan Dept Comp Syst Jamova Cesta 39 Ljubljana 1000 Slovenia

In this paper we present a novel data-driven subsampling method that can be seamlessly integrated into any neural network architecture to identify the most informative subset of samples within the original acquisition domain for a variety of tasks that rely on deep learning inference from sampled signals. In contrast to existing methods that require signal transformation into a sparse basis, expensive signal reconstruction as an intermediate step, and that can support a single predefined sampling rate only, our approach allows the sampling inference pipeline to adapt to multiple sampling rates directly in the original signal domain. The key innovations enabling such operation are a custom subsampling layer and a novel training mechanism. Through extensive experiments with four data sets and four different network architectures, our method demonstrates a simple yet powerful sampling strategy that allows the given network to be efficiently utilized at any given sampling rate, while the inference accuracy degrades smoothly and gradually as the sampling rate is reduced. Experimental comparison with state-of-the-art sparse sensing and learning techniques demonstrates competitive inference accuracy at different sampling rates, coupled with a significant improvement in computational efficiency, and the crucial ability to operate at arbitrary sampling rates without the need for retraining.

关键词： Nonuniform sampling Compressive sensing Deep learning EEG classification Speech recognition image classification

来源：评论

学校读者我要写书评

暂无评论

MFCA-MICNN: a convolutional neural network with multiscale fast channel attention and multibranch irregular convolution for noise removal in dMRI

引用

PHYSICS IN MEDICINE AND BIOLOGY 2024年第21期69卷 215003-215003页

作者： Ai, Lingmei Shi, Yunfan Yao, Ruoxia Li, Liangfu Shaanxi Normal Univ Sch Comp Sci 620West Changan Ave Xian 710119 Shaanxi Peoples R China

Diffusion magnetic resonance imaging (dMRI) currently stands as the foremost noninvasive method for quantifying brain tissue microstructure and reconstructing white matter fiber pathways. However, the inherent free diffusion motion of water molecules in dMRI results in signal decay, diminishing the signal-to-noise ratio (SNR) and adversely affecting the accuracy and precision of microstructural data. In response to this challenge, we propose a novel method known as the Multiscale Fast Attention-Multibranch Irregular Convolutional neural Network for dMRI image denoising. In this work, we introduce Multiscale Fast Channel Attention, a novel approach for efficient multiscale feature extraction with attention weight computation across feature channels. This enhances the model's capability to capture complex features and improves overall performance. Furthermore, we propose a multi-branch irregular convolutional architecture that effectively disrupts spatial noise correlation and captures noise features, thereby further enhancing the denoising performance of the model. Lastly, we design a novel loss function, which ensures excellent performance in both edge and flat regions. Experimental results demonstrate that the proposed method outperforms other state-of-the-art deep learning denoising methods in both quantitative and qualitative aspects for dMRI image denoising with fewer parameters and faster operational speed.

关键词： diffusion MRI medical image processing deep learning noise reduction convolutional neural network channel attention

来源：评论

学校读者我要写书评

暂无评论

Distributed source DOA estimation based on deep learning networks

引用

signal image AND VIDEO processing 2024年第10期18卷 7395-7403页

作者： Tian, Quan Cai, Ruiyan Qiu, Gongrun Luo, Yang Taizhou Univ Sch Elect & Informat Engn Taizhou 318000 Zhejiang Peoples R China Beijing 61618 Troops Beijing 100088 Peoples R China Peoples Liberat Army Gen Hosp Dept Orthoped Med Ctr 1 Beijing 100853 Peoples R China

With space electromagnetic environments becoming increasingly complex, the direction of arrival (DOA) estimation based on the point source model can no longer meet the requirements of spatial target location. Based on the characteristics of the distributed source, a new DOA estimation algorithm based on deep learning is proposed. The algorithm first maps the distributed source model into the point source model via a generative adversarial network (GAN) and further combines the subspace-based method to achieve central DOA estimation. Second, by constructing a deep neural network (DNN), the covariance matrix of the received signals is used as the input to estimate the angular spread of the distributed source. The experimental results show that the proposed algorithm can achieve better performance than the existing methods for a distributed source.

关键词： DOA estimation Distributed source Generative adversarial network Deep neural network

来源：评论

学校读者我要写书评

暂无评论

TPOT with SVM hybrid machine learning model for lung cancer classification using CT image

引用

BIOMEDICAL signal processing AND CONTROL 2025年 104卷

作者： Murthy, Nayana N. Thippeswamy, K. Visvesvaraya Technol Univ Dept Comp Sci & Engn Belagavi 590018 Karnataka India VTU PG Ctr Dept Comp Sci Engn Mysuru India Visvesvaraya Technol Univ Belagavi 590018 Karnataka India

Lung cancer arises when lung cells proliferate uncontrollably, creating tumors that may disrupt the normal functioning of the lungs. Accurate classification of lung cancer leads to earlier detection, which significantly improves treatment outcomes and survival rates. Diagnosing early-stage lung cancer is challenging due to its lack of symptoms and the high costs. Moreover, the previous methods struggle to fully understand and interpret the complex patterns in medical images. Therefore, this work develops the Tree-based Pipeline Optimization Tool with Support Vector Machine (TPOT_SVM) to classify lung cancer. Here, the Computed Tomography (CT) image is considered as input, and then Adaptive Median Filter (AMF) is employed for pre-processing. After this, the lung lobe is segmented by employing M-SegNet. Following this, the features, namely statistical features, Convolutional neural Network (CNN) features and textural features are mined. After this, the features are subjected to lung cancer classification, which is executed using the proposed TPOT_SVM. Here, TPOT_SVM is produced by integrating a Tree-based Pipeline Optimization Tool (TPOT) and Support Vector Machine (SVM). The TPOT_SVM attained an accuracy of 91.77%, a True Positive Rate (TPR) of 94.79% and a False Positive Rate (FPR) of 11.24%. The accuracy of the TPOT_SVM is 9.81%, 6.64%, 4.36%, 4.12%, 3.27%, 2.18%, 1.64% and 1.09% higher than the existing methods, such as Convolutional neural Network (CNN), Kernel Attribute Selected Classifier (KASC), Cat Swarm Optimization-Based Computer-Aided Diagnosis for lung cancer classification (CHO-CADLCC), SelfUpgraded Cat Mouse Optimizer with Machine Learning Driven Lung Cancer Classification (SCMO-MLL2C), Lung-EffNet, Gradient Boosting Classifier (GBC), TPOT and SVM.

关键词： Adaptive median filter Support vector machine M-SegNet Tree-based pipeline optimization tool Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Synthetic Reduced Nearest-Neighbor with Two-Layer neural Networks: A Step Forward in image Classification 37

Enhancing Synthetic Reduced Nearest-Neighbor with Two-Layer ...

引用

2024 International Workshop on signal processing Systems

作者： Alizadeh, Azar Singhal, Mukesh Univ Calif Merced Dept Elect Engn & Comp Sci Merced CA 95343 USA

ISBN: (纸本)9798350373769;9798350373752

Synthetic Reduced Nearest Neighbor (SRNN) models, operating exclusively on synthetic samples or prototypes, represent a significant stride in the field of nearest-neighbor algorithms. Central to this innovation is enhancing the interpretability and optimization of the model, achieved through specialized techniques. This study introduces a novel Two-Layer neural-SRNN model for classification tasks, diverging from traditional Expectation Maximization (EM) methodologies. The TLN-SRNN model significantly advances efficiency and scalability, outperforming traditional methods in speed while maintaining accuracy. Our empirical findings highlight the model's rapid convergence and robust performance across diverse datasets, establishing it as a notable innovation in the field of machine learning.

关键词： Classification Two-Layer neural SRNN neural networks neural SRNN Ensemble

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：