检索结果-内蒙古大学图书馆

Detail-Injection-Model-Inspired Deep Fusion Network for Pansharpening

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Xiang, Zhikang Xiao, Liang Yang, Jingxiang Liao, Wenzhi Philips, Wilfried Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Univ Ghent IMEC Image Proc & Interpretat IPI Res Grp B-9000 Ghent Belgium Flanders Make B-8500 Kortrijk Belgium Univ Ghent Dept Telecommun & Informat Proc TELIN B-9000 Ghent Belgium Univ Ghent IMEC IPI Res Grp B-9000 Ghent Belgium

Pansharpening is an image fusion procedure, which aims to produce a high spatial resolution multispectral (MS) image by combining a low spatial resolution MS image and a high spatial resolution panchromatic image. The most popular and successful paradigm for pansharpening is the framework known as detail injection, while it cannot fully exploit complex and nonlinear complementary features of both images. In this article, we propose a detail-injection-model-inspired deep fusion network for pansharpening (DIM-FuNet). First, by treating pansharpening as a complicated and nonlinear detail learning and injection problem, we establish a unified optimizing detail-injection model with triple detail fidelity terms: 1) a band-dependent spatial detail fidelity term;2) a local detail fidelity term;and 3) a complicated detail synthesis term. Second, the model is optimized via the iterative gradient descent and unfolded into a deep convolutional neural network. Subsequently, the unrolling network has triple branches, in which a point-wise convolutional subnetwork and a depth-wise convolutional subnetwork are corresponding to the former two detail-constrained terms, and an adaptive weighted reconstruction module with a fusion subnetwork to aggregate details of two branches and to synthesize the final complicated details. Finally, the deep unrolling network is trained in an end-to-end manner. Different from traditional deep fusion networks, the architecture design of DIM-FuNet is guided by the optimizing model and thus promotes better interpretability. Experimental results on reduced and full-resolution demonstrate the effectiveness of the proposed DIM-FuNet which achieves the best performance compared with the state-of-the-art pansharpening method.

关键词： Pansharpening Spatial resolution Iterative methods Image resolution Optimization Convolutional neural networks Remote sensing algorithm unrolling data fusion deep learning pansharpening remote sensing

来源：评论

学校读者我要写书评

暂无评论

ADMM-SLPNet: A Model-Driven Deep Learning Framework for Symbol-Level Precoding

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第1期73卷 1376-1381页

作者： Yang, Junwen Li, Ang Liao, Xuewen Masouros, Christos Xi An Jiao Tong Univ Fac Elect & Informat Engn Sch Informat & Commun Engn Xian 710049 Shaanxi Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China UCL Dept Elect & Elect Engn London WC1E 7JE England

Constructive interference (CI)-based symbol-level precoding (SLP) is an emerging downlink transmission technique for multi-antenna communications systems, and its low-complexity implementations are of practical importance. In this paper, we propose an interpretable model-driven deep learning framework to accelerate the processing of SLP. Specifically, the network topology is carefully designed by unrolling a parallelizable algorithm based on the proximal Jacobian alternating direction method of multipliers (PJ-ADMM), attaining parallel and distributed architecture. Moreover, the parameters of the iterative PJ-ADMM algorithm are untied to parameterize the network. By incorporating the problem-domain knowledge into the loss function, an unsupervised learning strategy is further proposed to discriminatively train the learnable parameters using unlabeled training data. Simulation results demonstrate significant efficiency improvement of the proposed ADMM-SLPNet over benchmark schemes.

关键词： Deep learning deep unfolding algorithm unrolling model-driven symbol-level precoding ADMM

来源：评论

学校读者我要写书评

暂无评论

Introducing Nonuniform Sparse Proximal Averaging Network for Seismic Reflectivity Inversion

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2023年 9卷 475-489页

作者： Mache, Swapnil Pokala, Praveen Kumar Rajendran, Kusala Seelamantula, Chandra Sekhar Indian Inst Sci Ctr Excellence Adv Mech Mat Bangalore 560012 India Indian Inst Sci Dept Elect Engn Bangalore 560012 India Univ Twente Biomed Photon Imaging Grp NL-7522 NB Enschede Netherlands Reliance Jio AICoE Hyderabad 500081 India Indian Inst Sci Ctr Earth Sci Bangalore 560012 India Indian Inst Sci Adv Mech Mat Bangalore 560012 India

We consider the problem of seismic reflectivity inversion, which pertains to the high-resolution recovery of interface locations and reflection coefficients from seismic measurements, which are vital for estimating the subsurface structure. We develop two model-based neural networks within the framework of deep-unfolding. First, we propose a nonuniform minimax concave penalty regularized formulation for reflectivity inversion and unfold the resulting iterative algorithm into a network. Second, we propose a nonuniform sparse model that relies on a combination of regularizers (composite regularization) and develop the nonuniform sparse proximal averaging network (NuSPAN). We demonstrate the efficacy of the proposed approaches over the benchmark techniques through numerical experiments on synthetic 1-D seismic traces and 2-D wedge models. We also report validations on the 2-D Marmousi2 simulated model and 3-D real field measurements from the Penobscot 3D survey off the coast of Nova Scotia, Canada. The accuracy of the proposed approaches is higher than the state-of-the-art techniques in terms of amplitude and support recovery. Further, for Marmousi2, the proposed deep-unfolding networks result in 600x faster inference than the fast iterative shrinkage-thresholding algorithm (FISTA). In terms of combined training and inference times, the learned iterative shrinkage-thresholding algorithm (LISTA) is the fastest. The inference speed-up is significant given that the volume of data is typically large in seismic signal processing.

关键词： algorithm unrolling geophysics non-convex optimization reflectivity inversion seismic imaging sparsity

来源：评论

学校读者我要写书评

暂无评论

Learning variational models with unrolling and bilevel optimization

引用

ANALYSIS AND APPLICATIONS 2024年第3期22卷 569-617页

作者： Brauer, Christoph Breustedt, Niklas de Wolff, Timo Lorenz, Dirk A. German Aerosp Ctr Inst Lightweight Syst Ottenbecker Damm 12 D-21684 Stade Germany Tech Univ Carolo Wilhelmina Braunschweig Inst Anal & Algebra Univ Pl 2 D-38106 Braunschweig Germany Univ Bremen Ctr Ind Math Postfach 330 440 D-28334 Bremen Germany

In this paper, we consider the problem of learning variational models in the context of supervised learning via risk minimization. Our goal is to provide a deeper understanding of the two approaches of learning of variational models via bilevel optimization and via algorithm unrolling. The former considers the variational model as a lower level optimization problem below the risk minimization problem, while the latter replaces the lower level optimization problem by an algorithm that solves said problem approximately. Both approaches are used in practice, but unrolling is much simpler from a computational point of view. To analyze and compare the two approaches, we consider a simple toy model, and compute all risks and the respective estimators explicitly. We show that unrolling can be better than the bilevel optimization approach, but also that the performance of unrolling can depend significantly on further parameters, sometimes in unexpected ways: While the stepsize of the unrolled algorithm matters a lot (and learning the stepsize gives a significant improvement), the number of unrolled iterations plays a minor role.

关键词： algorithm unrolling bilevel optimization supervised learning risk minimization

来源：评论

学校读者我要写书评

暂无评论

MODEL-INSPIRED DEEP LEARNING FOR LIGHT-FIELD MICROSCOPY WITH APPLICATION TO NEURON LOCALIZATION

MODEL-INSPIRED DEEP LEARNING FOR LIGHT-FIELD MICROSCOPY WITH...

引用

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

作者： Song, Pingfan Jadan, Herman Verinaz Howe, Carmel L. Quicke, Peter Foust, Amanda J. Dragotti, Pier Luigi Imperial Coll London Dept Elect & Elect Engn London England Imperial Coll London Dept Bioengn London England Imperial Coll London Ctr Neurotechnol London England

ISBN: (纸本)9781728176055

Light-field microscopes are able to capture spatial and angular information of incident light rays. This allows reconstructing 3D locations of neurons from a single snap-shot. In this work, we propose a model-inspired deep learning approach to perform fast and robust 3D localization of sources using light-field microscopy images. This is achieved by developing a deep network that efficiently solves a convolutional sparse coding (CSC) problem to map Epipolar Plane Images (EPI) to corresponding sparse codes. The network architecture is designed systematically by unrolling the convolutional Iterative Shrinkage and Thresholding algorithm (ISTA) while the network parameters are learned from a training dataset. Such principled design enables the deep network to leverage both domain knowledge implied in the model, as well as new parameters learned from the data, thereby combining advantages of model-based and learning-based methods. Practical experiments on localization of mammalian neurons from light-fields show that the proposed approach simultaneously provides enhanced performance, interpretability and efficiency.

关键词： Light-field microscopy model-inspired deep learning algorithm unrolling sparse coding

来源：评论

学校读者我要写书评

暂无评论

Decentralized Statistical Inference with Unrolled Graph Neural Networks 60

Decentralized Statistical Inference with Unrolled Graph Neur...

引用

60th IEEE Conference on Decision and Control (CDC)

作者： Wang, He Shen, Yifei Wang, Ziyuan Li, Dongsheng Zhang, Jun Letaief, Khaled B. Lu, Jie ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai 200050 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Microsoft Res Asia Shanghai Peoples R China Hong Kong Polytech Univ Dept Elect & Informat Engn Hong Kong Peoples R China

ISBN: (纸本)9781665436595

In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination. Existing optimization-based algorithms suffer from issues of model mismatches and poor convergence speed, and thus their performance would be degraded provided that the number of communication rounds is limited. This motivates us to propose a learning-based framework, which unrolls well-noted decentralized optimization algorithms (e.g., Prox-DGD and PG-EXTRA) into graph neural networks (GNNs). By minimizing the recovery error via end-to-end training, this learning-based framework resolves the model mismatch issue. Our convergence analysis (with PG-EXTRA as the base algorithm) reveals that the learned model parameters may accelerate the convergence and reduce the recovery error to a large extent. The simulation results demonstrate that the proposed GNN-based learning methods prominently outperform several state-of-the-art optimization-based algorithms in convergence speed and recovery error.

关键词： Decentralized optimization graph neural networks algorithm unrolling interpretable deep learning

来源：评论

学校读者我要写书评

暂无评论

SAR SUPER-RESOLUTION USING PHYSICS-AWARE ADAPTIVE COMPRESSED SENSING

SAR SUPER-RESOLUTION USING PHYSICS-AWARE ADAPTIVE COMPRESSED...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Guha, Sanhita Datcu, Mihai Ender, Joachim Fraunhofer Inst High Frequency Phys & Radar Tech Wachtberg Germany German Aerosp Ctr DLR Oberpfaffenhofen Germany

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

The resolution requirements of modern radar applications are increasing rapidly and cannot be fulfilled by the limited number of wide-band radar systems. Many approaches have been explored to solve this problem under the topic of super-resolution. In this paper, we propose a hybrid algorithm for resolution improvement, where we aim to combine the adaptability of deep neural networks with the reliability and expertise of traditional domain-specific SAR processing.

关键词： ISTA Learned ISTA Approximated Observation SAR Super-resolution,High resolution radar algorithm unrolling Hybrid Approaches to Super-resolution

来源：评论

学校读者我要写书评

暂无评论

unrolling Alternating Direction Method of Multipliers for Visible and Infrared Image Fusion 5

Unrolling Alternating Direction Method of Multipliers for Vi...

引用

5th IEEE International Conference on Image Processing Applications and Systems (IPAS)

作者： Bakan, Altug Erer, Isin Istanbul Tech Univ Dept Elect & Commun Engn Istanbul Turkey ASELSAN Microelect Guidance & Electroopt Business Sect Ankara Turkey

ISBN: (纸本)9781665462198

In this paper a new infrared and visible image fusion (IVIF) method which combines the advantages of optimization and deep learning based methods is proposed. This model takes the iterative solution used by the alternating direction method of the multiplier (ADMM) optimization method, and uses algorithm unrolling to obtain a high performance and efficient algorithm. Compared with traditional optimization methods, this model generates fusion with 99.6% improvement in terms of image fusion time, and compared with deep learning based algorithms, this model generates detailed fusion images with 99.1% improvement in terms of training time. Compared with the other state-of-the-art unrolling based methods, this model performs 26.7% better on average in terms of Average Gradient (AG), Cross Entropy (CE), Mutual Information (MI), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Loss (SSIM) metrics with a minimal testing time cost.

关键词： visible and infrared image fusion algorithm unrolling model based deep network ADMM

来源：评论

学校读者我要写书评

暂无评论

GRAPH SIGNAL DENOISING VIA unrolling NETWORKS

GRAPH SIGNAL DENOISING VIA UNROLLING NETWORKS

引用

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

作者： Chen, Siheng Eldar, Yonina C. Mitsubishi Elect Res Labs Cambridge MA 02139 USA Weizmann Inst Sci Rehovot Israel

ISBN: (纸本)9781728176055

We propose an interpretable graph neural network framework to denoise single or multiple noisy graph signals. The proposed graph unrolling networks expand algorithm unrolling to the graph domain and provide an interpretation of the architecture design from a signal processing perspective. We unroll an iterative denoising algorithm by mapping each iteration into a single network layer where the feed-forward process is equivalent to iteratively denoising graph signals. We train the graph unrolling networks through unsupervised learning, where the input noisy graph signals are used to supervise the networks. By leveraging the learning ability of neural networks, we adaptively capture appropriate priors from input noisy graph signals, instead of manually choosing signal priors. To validate the proposed methods, we conduct extensive experiments on both real-world datasets and simulated datasets, and demonstrate that our methods have smaller denoising errors than conventional denoising algorithms and state-of-the-art graph neural networks. For denoising a single smooth graph signal, the normalized mean square error of the proposed networks is around 40% and 60% lower than that of graph Laplacian denoising and graph wavelets, respectively.

关键词： Graph signal denoising algorithm unrolling graph neural networks

来源：评论

学校读者我要写书评

暂无评论

unrolling PARTICLES: UNSUPERVISED LEARNING OF SAMPLING DISTRIBUTIONS 47

UNROLLING PARTICLES: UNSUPERVISED LEARNING OF SAMPLING DISTR...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Gama, Fernando Zilberstein, Nicolas Baraniuk, Richard G. Segarra, Santiago Rice Univ Dept Elect & Comp Engn POB 1892 Houston TX 77251 USA

ISBN: (纸本)9781665405409

Particle filtering is used to compute nonlinear estimates of complex systems. It samples trajectories from a chosen distribution and computes the estimate as a weighted average of them. Easy-to-sample distributions often lead to degenerate samples where only one trajectory carries all the weight, negatively affecting the resulting performance of the estimate. While much research has been done on the design of appropriate sampling distributions that would lead to controlled degeneracy, in this paper our objective is to learn sampling distributions. Leveraging the framework of algorithm unrolling, we model the sampling distribution as a multivariate normal, and we use neural networks to learn both the mean and the covariance. We carry out unsupervised training of the model to minimize weight degeneracy, relying only on the observed measurements of the system. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.

关键词： algorithm unrolling particle filtering unsupervised learning

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：