检索结果-内蒙古大学图书馆

6th International Conference on Information Communication and Signal Processing, ICICSP 2023

作者： Zhang, Han Lin, Jianbo Du, Zhaohui Li, Yunfei School of Construction Machinery Chang'an University Xi'an China School of Marine Science and Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350339994

The deconvolution method (DM) is an effective tool for enhancing the impulsive features of rolling bearings. Deep network-based deconvolution methods transform complex numerical computations into network optimization, improving the performance of DMs. However, current deep deconvolution methods do not consider the possibility of utilizing nonlinear operations to further enhance the performance. Inspired by convolutional sparse learning and algorithm unfolding, a bearing fault feature extraction method, Multi D-norm driven algorithm unfolding network (MDN-AUN) is proposed. First, a convolutional sparse coding model is established with the fault impulse as the target sparse code. Then the Iterative Soft Thresholding algorithm (ISTA) for solving the model is unfolded from the iterative direction and the algorithm unfolding network is generated. Finally, the multi D-norm, which can evaluate the periodicity and impulsiveness of the signal, is chosen as the objective function of the sparse code to train the neural network. MDN-AUN is compared with several deconvolution methods through simulation and real vibration signals. The results show that MDN-AUN has the superior ability to enhance the impulsive features, and the fault diagnosis performance is significantly better than the compared methods. © 2023 IEEE.

关键词： algorithm unfolding bearing fault diagnosis deconvolution method iterative soft thresholding algorithm multi D-norm

来源：评论

学校读者我要写书评

暂无评论

A Variational Neural Network Based on algorithm unfolding for Image Blind Deblurring

引用

APPLIED SCIENCES-BASEL 2024年第24期14卷 11742页

作者： Gong, Shaoqing Wang, Yeran Yang, Guangyu Wei, Weibo Zhao, Junli Pan, Zhenkuan Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China

Image blind deblurring is an ill-posed inverse problem in image processing. While deep learning approaches have demonstrated effectiveness, they often lack interpretability and require extensive data. To address these limitations, we propose a novel variational neural network based on algorithm unfolding. The model is solved using the half quadratic splitting (HQS) method and proximal gradient descent. For blur kernel estimation, we introduce an L0 regularizer to constrain the gradient information and use the fast fourier transform (FFT) to solve the iterative results, thereby improving accuracy. Image restoration is initiated with Gabor filters for the convolution kernel, and the activation function is approximated using a Gaussian radial basis function (RBF). Additionally, two attention mechanisms improve feature selection. The experimental results on various datasets demonstrate that our model outperforms state-of-the-art algorithm unfolding networks and other blind deblurring models. Our approach enhances interpretability and generalization while utilizing fewer data and parameters.

关键词： image blind deblurring algorithm unfolding regularizer neural network variational model

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT POWER ALLOCATION USING GRAPH NEURAL NETWORKS AND DEEP algorithm unfolding

EFFICIENT POWER ALLOCATION USING GRAPH NEURAL NETWORKS AND D...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Chowdhury, Arindam Verma, Gunjan Rao, Chirag Swami, Ananthram Segarra, Santiago Rice Univ Houston TX 77251 USA US Armys CCDC Army Res Lab Adelphi MD USA

ISBN: (纸本)9781728176055

We study the problem of optimal power allocation in a single-hop ad hoc wireless network. In solving this problem, we propose a hybrid neural architecture inspired by the algorithmic unfolding of the iterative weighted minimum mean squared error (WMMSE) method, that we denote as unfolded WMMSE (UWMMSE). The learnable weights within UWMMSE are parameterized using graph neural networks (GNNs), where the time-varying underlying graphs are given by the fading interference coefficients in the wireless network. These GNNs are trained through a gradient descent approach based on multiple instances of the power allocation problem. Once trained, UWMMSE achieves performance comparable to that of WMMSE while significantly reducing the computational complexity. This phenomenon is illustrated through numerical experiments along with the robustness and generalization to wireless networks of different densities and sizes.

关键词： Wireless network power allocation WMMSE graph neural network algorithm unfolding

来源：评论

学校读者我要写书评

暂无评论

Optimization algorithm unfolding Deep Networks of Detail Injection Model for Pansharpening

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Feng, Yunqiao Liu, Junmin Chen, Kun Wang, Bo Zhao, Zixiang Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China Harbin Engn Univ Natl Key Lab Sci & Technol Underwater Vehicle Harbin 150001 Peoples R China

Pansharpening aims at integrating a high-spatial-resolution panchromatic (PAN) image with a low-spatial-resolution multispectral (MS) image to generate a high-resolution MS (HRMS) image. It is a fundamental and significant task in the field of remotely sensed images. Classic and convolutional neural network (CNN)-based algorithms have been developed, over the last decades, for pansharpening based on the spatial detail injection model. However, these algorithms have difficulties in extracting sufficient details or lack interpretability. In this letter, we present an algorithm unfolding pansharpening (AUP) for this task. In the proposed AUP, a two-step optimization model is first designed based on the spatial detail decomposition model. Then, the iteration processes induced by an optimization model are mapped to several detailed convolution (dc) blocks to solve the detail injection by a trainable neural network. Finally, the desired MS details are obtained in end-to-end manners through a decoder. The superiority of the proposed AUP is demonstrated by extensive experiments on datasets acquired by two different kinds of satellites. Each module of the AUP is interpretable, and its fused results are with fewer spectral and spatial distortions.

关键词： Pansharpening Optimization Neural networks Convolution Tensors Signal processing algorithms Uncertainty algorithm unfolding deep neural networks details injection pansharpening

来源：评论

学校读者我要写书评

暂无评论

Deep unfolding Multi-Modal Image Fusion Network via Attribution Analysis

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 3498-3511页

作者： Bai, Haowen Zhao, Zixiang Zhang, Jiangshe Jiang, Baisong Deng, Lilun Cui, Yukun Xu, Shuang Zhang, Chunxia Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Shaanxi Peoples R China Swiss Fed Inst Technol Photogrammetry & Remote Sensing CH-8093 Zurich Switzerland North western Polytech Univ Sch Math & Stat Xian 710072 Shaanxi Peoples R China

Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primarily focus on acquiring informative fusion images at the visual display stratum through intricate mappings. Although some approaches attempt to jointly optimize image fusion and downstream tasks, these efforts often lack direct guidance or interaction, serving only to assist with a predefined fusion loss. To address this, we propose an "unfolding Attribution Analysis Fusion network" (UAAFusion), using attribution analysis to tailor fused images more effectively for semantic segmentation, enhancing the interaction between the fusion and segmentation. Specifically, we utilize attribution analysis techniques to explore the contributions of semantic regions in the source images to task discrimination. At the same time, our fusion algorithm incorporates more beneficial features from the source images, thereby allowing the segmentation to guide the fusion process. Our method constructs a model-driven unfolding network that uses optimization objectives derived from attribution analysis, with an attribution fusion loss calculated from the current state of the segmentation network. We also develop a new pathway function for attribution analysis, specifically tailored to the fusion tasks in our unfolding network. An attribution attention mechanism is integrated at each network stage, allowing the fusion network to prioritize areas and pixels crucial for high-level recognition tasks. Additionally, to mitigate the information loss in traditional unfolding networks, a memory augmentation module is incorporated into our network to improve the information flow across various network layers. Extensive experiments demonstrate our method's superiority in image fusion and applicability to semantic segmentation. The code is available at https://***/HaowenBai/UAAFusion.

关键词： Multi-modal image fusion algorithm unfolding attribution analysis attribution analysis memory augmentation memory augmentation memory augmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Graph unfolding for Beamforming in MU-MIMO Interference Networks

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第5期23卷 4889-4903页

作者： Chowdhury, Arindam Verma, Gunjan Swami, Ananthram Segarra, Santiago Rice Univ Dept Elect & Comp Engn Houston TX 77005 USA US Armys DEVCOM Army Res Lab Adelphi MD 20783 USA

We develop an efficient and near-optimal solution for beamforming in multi-user multiple-input-multiple-output single-hop wireless ad-hoc interference networks. Inspired by the weighted minimum mean squared error (WMMSE) method, a classical approach to solving this problem, and the principle of algorithm unfolding, we present unfolded WMMSE (UWMMSE) for MU-MIMO. This method learns a parameterized functional transformation of key WMMSE variables using graph neural networks (GNNs), where the channel and interference components of a wireless network constitute the underlying graph. These GNNs are trained through gradient descent on a network utility metric using multiple instances of the beamforming problem. Comprehensive experimental analyses illustrate the superiority of UWMMSE over the classical WMMSE and state-of-the-art learning-based methods in terms of performance, generalizability, and robustness.

关键词： Beamforming WMMSE algorithm unfolding complex-valued graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 3272-3286页

作者： Shah, Shaik Basheeruddin Pradhan, Pradyumna Pu, Wei Randhi, Ramunaidu Rodrigues, Miguel R. D. Eldar, Yonina C. Weizmann Inst Sci IL-7610001 Rehovot Israel Indian Inst Petr & Energy Dept Humanities & Sci Visakhapatnam 530003 India Univ Elect Sci & Technol Chengdu 610054 Peoples R China UCL Dept Elect & Elect Engn London WC1H 9BT England

Solving linear inverse problems plays a crucial role in numerous applications. algorithm unfolding based, model-aware data-driven approaches have gained significant attention for effectively addressing these problems. Learned iterative soft-thresholding algorithm (LISTA) and alternating direction method of multipliers compressive sensing network (ADMM-CSNet) are two widely used such approaches, based on ISTA and ADMM algorithms, respectively. In this work, we study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs, for finite-layer unfolded networks such as LISTA and ADMM-CSNet with smooth soft-thresholding in an over-parameterized (OP) regime. We achieve this by leveraging a modified version of the Polyak-& Lstrok;ojasiewicz, denoted PL*, condition. Satisfying the PL* condition within a specific region of the loss landscape ensures the existence of a global minimum and exponential convergence from initialization using gradient descent based methods. Hence, we provide conditions, in terms of the network width and the number of training samples, on these unfolded networks for the PL* condition to hold, by deriving the Hessian spectral norm. Additionally, we show that the threshold on the number of training samples increases with the increase in the network width. Furthermore, we compare the threshold on training samples of unfolded networks with that of a standard fully-connected feed-forward network (FFNN) with smooth soft-thresholding non-linearity. We prove that unfolded networks have a higher threshold value than FFNN. Consequently, one can expect a better expected error for unfolded networks than FFNN.

关键词： Training Vectors Optimization Convergence Computational modeling Signal processing algorithms Mathematical models Optimization guarantees algorithm unfolding LISTA ADMM-CSNet Polyak-& Lstrok ojasiewicz condition

来源：评论

学校读者我要写书评

暂无评论

Joint Precoding and CSI Dimensionality Reduction: An Efficient Deep unfolding Approach

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第12期22卷 9502-9516页

作者： Zhang, Jianjun Masouros, Christos Hanzo, Lajos Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China UCL Dept Elect & Elect Engn London WC1E7JE England Univ Southampton Dept Elect & Comp Sci Southampton SO171BJ England

A recently proposed unified precoding and pilot design optimization (UPPiDO) framework offers a reduction in both training and feedback overhead of acquiring channel state information (CSI) and an enhancement in robustness (to CSI uncertainties) at the expense of a more computationally demanding precoding optimization. To address this increased complexity, in this paper we first propose an unfolding-friendly iterative algorithm, which can efficiently address a family of non-convex and non-smooth problems. Then, we develop an efficient approach to unfold the iterative algorithm designed. Besides being applicable to important and typical iterative optimization algorithms, a pivotal advantage of the proposed unfolding approach is that the trainable parameters are scalars (rather than matrices). This, in turn, reduces the number of training samples required and makes it suitable for rapidly fluctuating wireless environments. We apply the algorithm unfolding (AU) techniques developed to our UPPiDO-based symbol-level precoding and block-level precoding. Our complexity analysis indicates that the computational complexity is scalable both with the numbers of served users and antennas. Our simulation results demonstrate that the number of outer iterations (or layers) required is about 1/3 of that of the original iterative algorithms.

关键词： Precoding Optimization Gold Complexity theory Iterative algorithms Wireless communication Training algorithm unfolding symbol-level precoding block-level precoding MIMO communications unified precoding and pilot design optimization complexity reduction

来源：评论

学校读者我要写书评

暂无评论

unfolding Gradient Graph Regularization for Point Cloud Color Denoising 7th

Unfolding Gradient Graph Regularization for Point Cloud Colo...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Wang, Hongtao Chen, Fei Liu, Wanling Zeng, Xunxun Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Fuzhou Univ Sch Math & Stat Fuzhou 350108 Peoples R China

ISBN: (纸本)9789819785070;9789819785087

Due to the cost and accuracy of current point cloud sampling equipment, the obtained point color information is often corrupted by various noises. Existing point cloud denoising algorithms mainly focus on smoothness priors and convex optimization. Their performances highly depend on model parameters whose values are determined manually and fixed throughout the iterations. In this paper, we propose to unfold gradient graph regularization with deep neural networks for point cloud color denoising. It improves the robustness of the model for denoising in different kinds of datasets and across domains. Specifically, our approach first uses a point cloud extraction network to obtain effective features for gradient computation. Then, we construct a gradient graph Laplacian regularization (GGLR) as signal smoothness prior to point cloud restoration. Finally, we introduce shallow neural networks for model parameter estimation to unfold GGLR. The proposed point cloud denoising framework is fully differentiable and can be trained end-to-end. Experiments show that the proposed algorithm unfolding outperforms several existing point cloud color denoising techniques.

关键词： Point cloud Color denoising Graph signal processing algorithm unfolding

来源：评论

学校读者我要写书评

暂无评论

Half-Split ResUNet Denoiser Based Deep Unrolling For Photon Limited Image Deblurring 15

Half-Split ResUNet Denoiser Based Deep Unrolling For Photon ...

引用

15th International Conference on Signal Processing and Communications (SPCOM)

作者： Kumar, Koyyada Dinesh Sahoo, Sujit Kumar Indian Inst Technol Goa Sch Elect Sci Ponda 403401 India

ISBN: (纸本)9798350350463;9798350350456

Photon-limited deblurring is a complex and demanding problem encountered in various applications where low-light conditions prevail. The scarcity of photons in such situations leads to the introduction of shot noise, resulting in a degradation of image quality. Solving this problem with Neural networks often involves constructing models empirically, making the behavior of the underlying architecture challenging to comprehend. A recent technique known as algorithm unrolling has enabled the connection of iterative algorithms with neural networks, where the Convolutional Neural Network (CNN) acts as a denoiser. This paper introduces a reduced parameter denoiser to enhance image quality and preserve finer details or avoid over-smoothing of the image during reconstruction. As a result, the unrolled model surpasses existing deblurring methods for improving image quality in low-light conditions. The proposed denoiser reduces the number of parameters by a factor of 3.84 and preserves the finer details while reconstructing. Our model improves computational efficiency and storage requirements compared to the state-of-the-art.

关键词： Photon limited Poisson deconvolution non-blind deblurring algorithm unfolding plug and play

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：