检索结果-内蒙古大学图书馆

30th European Signal Processing Conference (EUSIPCO)

作者： Koo, Jakeoung Halimi, Abderrahim Maccarone, Aurora Buller, Gerald S. McLaughlin, Stephen Heriot Watt Univ Sch Engn & Phys Sci Edinburgh Midlothian Scotland

ISBN: (纸本)9789082797091

In this paper, we propose a deep learning model for 3D single-photon Lidar imaging through obscurants, i.e., in the presence of a high and non-uniform background. The proposed method unrolls the iterative steps of a Bayesian based-algorithm into the layers of a deep neural network. To deal with imaging through obscurants, the method first unmix signal and background photons in a pre-processing step. Following this, the method builds on multiscale information to improve robustness to noise and uses the attention framework for scale selection within the network. Experimental results on simulated and real underwater data demonstrate that our method can estimate accurate depth maps in challenging situations with a high non-uniform background. Compared to state-of-the-art deep learning methods, the proposed method enables an estimation of parameters uncertainties, suitable for decision making.

关键词： 3D reconstruction single-photon imaging Lidar obscurants algorithm unrolling attention

来源：评论

学校读者我要写书评

暂无评论

BAYESIAN DEEP UNFOLDING WITH GRAPH ATTENTION FOR DUAL-PEAK SINGLE-PHOTON LIDAR IMAGING 32

BAYESIAN DEEP UNFOLDING WITH GRAPH ATTENTION FOR DUAL-PEAK S...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Koo, JaKeoung Halimi, Abderrahim McLaughlin, Stephen Gachon Univ Sch Comp Seongnam South Korea Heriot Watt Univ Edinburgh Midlothian Scotland

ISBN: (纸本)9789464593617;9798331519773

Single-photon Lidar is a promising 3D imaging technique, but it is challenging to deploy in real-world applications due to high noise levels and the presence of multiple surfaces per pixel. Existing statistical methods are interpretable, but limited by the assumed model. Data-driven approaches show excellent performance, but with limited interpretability, preventing their use in critical applications. In this paper, we propose an interpretable deep learning architecture with graph attention networks for the reconstruction of dual peaks per pixel in single photon Lidar. Instead of the conventional image-based representation, we represent the solution as point clouds, allowing reconstruction of more than one surface per pixel. The proposed architecture is based on a statistical Bayesian algorithm, whose iterative steps are converted into neural network layers. This approach combines the advantages of both statistical and learning-based frameworks, providing good estimates with improved network interpretability. Experimental results demonstrate the effectiveness of the proposed method.

关键词： 3D reconstruction single-photon imaging Lidar obscurants algorithm unrolling attention 3D reconstruction Single-photon lidar Single-photon imaging algorithm unrolling Geometric deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Electrical Impedance Tomography Reconstruction Using Learned Half-Quadratic Splitting Networks with Anderson Acceleration

引用

JOURNAL OF SCIENTIFIC COMPUTING 2024年第2期98卷 49-49页

作者： Xu, Guixian Wang, Huihui Zhou, Qingping Cent South Univ Sch Math & Stat HNP LAMA Changsha Peoples R China

Electrical Impedance Tomography (EIT) is widely applied in medical diagnosis, industrial inspection, and environmental monitoring. Combining the physical principles of the imaging system with the advantages of data-driven deep learning networks, physics-embedded deep unrolling networks have recently emerged as a promising solution in computational imaging. However, the inherent nonlinear and ill-posed properties of EIT image reconstruction still present challenges to existing methods in terms of accuracy and stability. To tackle this challenge, we propose the learned half-quadratic splitting (HQSNet) algorithm for incorporating physics into learning-based EIT imaging. We then apply Anderson acceleration (AA) to the HQSNet algorithm, denoted as AA-HQSNet, which can be interpreted as AA applied to the Gauss-Newton step and the learned proximal gradient descent step of the HQSNet, respectively. AA is a widely-used technique for accelerating the convergence of fixed-point iterative algorithms and has gained significant interest in numerical optimization and machine learning. However, the technique has received little attention in the inverse problems community thus far. Employing AA enhances the convergence rate compared to the standard HQSNet while simultaneously avoiding artifacts in the reconstructions. Lastly, we conduct rigorous numerical and visual experiments to show that the AA module strengthens the HQSNet, leading to robust, accurate, and considerably superior reconstructions compared to state-of-the-art methods. Our Anderson acceleration scheme to enhance HQSNet is generic and can be applied to improve the performance of various physics-embedded deep learning methods.

关键词： Nonlinear inverse problems algorithm unrolling Anderson acceleration Half-quadratic splitting Electrical impedance tomography

来源：评论

学校读者我要写书评

暂无评论

Unrolled Network for Light Field Display

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2022年第10期E105D卷 1721-1725页

作者： Matsuura, Kotaro Tsutake, Chihiro Takahashi, Keita Fujii, Toshiaki Nagoya Univ Grad Sch Engn Nagoya 4648603 Japan

Inspired by the framework of algorithm unrolling, we pro-pose a scalable network architecture that computes layer patterns for light field displays, enabling control of the trade-off between the display quality and th... 详细信息

关键词： 3D display light field algorithm unrolling

来源：评论

学校读者我要写书评

暂无评论

Deep Interpretable Fully CNN Structure for Sparse Hyperspectral Unmixing via Model-Driven and Data-Driven Integration

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023年 61卷 1-1页

作者： Kong, Fanqiang Chen, Mengyue Li, Yunsong Li, Dan Zheng, Yuhan Nanjing Univ Aeronaut & Astronaut Coll Astronaut Nanjing 210016 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xidian 710071 Peoples R China

Hyperspectral unmixing (HSU), which aims to identify constituent materials and estimate the corresponding proportions in a scene, is an essential research topic in remote sensing. Most deep learning-based methods are data-inspired, relying on massive amounts of data to train black-box-like networks, while a few model-inspired unmixing networks only consider the spectral features of the pixel, ignoring the exploration of spatial information between pixels. In this article, we design a network topology according to the classical iterative algorithm, and the large number of learnable parameters contained in the network is continuously updated through data fitting. In other words, we integrate the concepts of both model- and data-driven and propose a deep interpretable fully convolutional neural network (DIFCNN). The iteration of the classic sparse unmixing algorithm is unfolded to provide guidance for the network structure and incorporate prior knowledge into the network. Meanwhile, 2-D convolutional layers are employed to automatically learn the spatial information at different scales. A known spectral library is used as a prior to initialize network parameters and reconstruct the image. The DIFCNN adopts an end-to-end training strategy;in addition, we establish a new loss function that adds a joint sparse constraint on the abundance result to the cross-entropy loss. Experiments on both synthetic and real datasets show that the performance of the DIFCNN not only outperforms the sparse unmixing by variable splitting and augmented Lagrangian (SUnSAL) and its improved algorithms but also is highly competitive in the state-of-the-art methods of deep learning.

关键词： algorithm unrolling convolutional neural network (CNN) hyperspectral unmixing (HSU) model-driven spectral-spatial

来源：评论

学校读者我要写书评

暂无评论

LADMM-Net: An unrolled deep network for spectral image fusion from compressive data

引用

SIGNAL PROCESSING 2021年 189卷 108239-108239页

作者： Ramirez, Juan Marcos Martinez-Torre, Jose Ignacio Arguello, Henry Univ Rey Juan Carlos Comp Sci Dept Mostoles Spain Univ Ind Santander Comp Sci Dept Bucaramanga Colombia

Image fusion aims at estimating a high-resolution spectral image from a low-spatial-resolution hyper spectral image and a low-spectral-resolution multispectral image. In this regard, compressive spectral imaging (CSI) has emerged as an acquisition framework that captures the relevant information of spectral images using a reduced number of measurements. Recently, various image fusion methods from CSI measurements have been proposed. However, these methods exhibit high running times and face the challenging task of choosing sparsity-inducing bases. In this paper, a deep network under the algorithm unrolling approach is proposed for fusing spectral images from compressive measurements. This architecture, dubbed LADMM-Net, casts each iteration of a linearized version of the alternating direction method of multipliers into a processing layer whose concatenation deploys a deep network. The linearized approach enables obtaining fusion estimates without resorting to costly matrix inversions. Furthermore, this approach exploits the benefits of learnable transforms to estimate the image details included in both the auxiliary variable and the Lagrange multiplier. Finally, the performance of the proposed technique is evaluated on two spectral image databases and one dataset captured at the laboratory. Extensive simulations show that the proposed method outperforms the state-of-the-art approaches that fuse spectral images from compressive measurements. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://***/licenses/by-nc-nd/4.0/ )

关键词： ADMM algorithm unrolling Compressive spectral imaging Deep network Image fusion

来源：评论

学校读者我要写书评

暂无评论

Learning-Based High-Frame-Rate SAR Imaging

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023年 61卷 1页

作者： Wu, Junjie Pu, Wei An, Hongyang Huang, Yulin Yang, Haiguang Yang, Jianyu Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Peoples R China

As high-frame-rate synthetic aperture radar (SAR) has the ability to form continuous SAR images and dynamically monitor the ground areas of interest, it has attracted more and more attention nowadays. In practical applications, the enormous data in high-frame-rate SAR system to obtain the multiframe images brings big challenges to its transmission, storage, and processing. In order to solve this problem, there are many recent papers on formulating the high-frame-rate SAR imaging problem into a low-rank tensor recovery problem, and correspondingly, the sampling amount of the high-frame-rate SAR data can be largely reduced. However, existing algorithms to solve the low-rank tensor recovery problem in high-frame-rate SAR application still suffer from large computational cost. Under the above inspiration, this article proposes a deep neural network architecture for high-frame-rate SAR imaging, i.e., tensor alternating direction method of multiplier network (TADMM-Net), which is more computationally efficient in the imaging procedure. Specifically, we formulate the high-frame-rate SAR imaging processing into a low-tubal-rank tensor recovery problem. We solve the low-tubal-rank tensor recovery problem using a tensor alternating direction method of multiplier (ADMM) algorithm and then design a new deep neural network architecture by applying algorithm unfolding techniques to the underlying low-rank tensor recovery problem. The proposed TADMM-Net approach shifts the computational burden from the testing phase to the training phase, and the practical processing time can be extremely decreased compared with the existing algorithms for the low-rank tensor recovery problem in high-frame-rate SAR imaging applications. It also offers various advantages over the existing high-frame-rate SAR imaging algorithms, including higher performance in the case with low sampling amount, lower storage complexity, and no requirement for handcraft hyperparameters adjustment. The methodology was

关键词： Tensors Radar polarimetry Synthetic aperture radar Imaging Optimization Signal processing algorithms Signal processing algorithm unrolling deep neural network high-frame-rate synthetic aperture radar (SAR) tensor alternating direction method of multiplier network (TADMM-Net)

来源：评论

学校读者我要写书评

暂无评论

Learning to optimize: a primer and a benchmark

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 8562-8620页

作者： Tianlong Chen Xiaohan Chen Wuyang Chen Zhangyang Wang Howard Heaton Jialin Liu Wotao Yin Department of Electrical and Computer and Engineering The University of Texas at Austin Austin TX Typal Research Typal LLC Los Angeles CA Alibaba US Damo Academy Decision Intelligence Lab Bellevue WA

Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on its performance on a set of training problems. This data-driven procedure generates methods that can efficiently solve problems similar to those in training. In sharp contrast, the typical and traditional designs of optimization methods are theory-driven, so they obtain performance guarantees over the classes of problems speci_ed by the theory. The difference makes L2O suitable for repeatedly solving a particular optimization problem over a specific distribution of data, while it typically fails on out-of-distribution problems. The practicality of L2O depends on the type of target optimization, the chosen architecture of the method to learn, and the training procedure. This new paradigm has motivated a community of researchers to explore L2O and report their *** article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization. We set up taxonomies, categorize existing works and research directions, present insights, and identify open challenges. We benchmarked many existing L2O approaches on a few representative optimization problems. For reproducible research and fair benchmarking purposes, we released our software implementation and data in the package Open-L2O.

关键词： learning to optimize meta learning optimization algorithm unrolling

来源：评论

学校读者我要写书评

暂无评论

Learning the sparse prior: Modern approaches

引用

Wiley Interdisciplinary Reviews: Computational Statistics 2024年第1期16卷 e1646-e1646页

作者： Peng, Guan-Ju Institute of Data Science and Information Computing National Chung Hsing University Taichung Taiwan

The sparse prior has been widely adopted to establish data models for numerous applications. In this context, most of them are based on one of three foundational paradigms: the conventional sparse representation, the convolutional sparse representation, and the multi-layer convolutional sparse representation. When the data morphology has been adequately addressed, a sparse representation can be obtained by solving the sparse coding problem specified by the data model. This article presents a comprehensive overview of these three models and their corresponding sparse coding problems and demonstrates that they can be solved using convex and non-convex optimization approaches. When the data morphology is not known or cannot be analyzed, it must be learned from training data, thereby formulating dictionary learning problems. This article addresses two different dictionary learning paradigms. In an unsupervised scenario, dictionary learning involves the alternating or joint resolution of sparse coding and dictionary updating. Another option is to create a recurrent neural network by unrolling algorithms designed to solve sparse coding problems. These networks can then be used in a supervised learning setting to facilitate the training of dictionaries via forward-backward optimization. This article lists numerous applications in various domains and outlines several directions for future research related to the sparse prior. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods Statistical and Graphical Methods of Data Analysis > Modeling Methods and algorithms Statistical Models > Nonlinear Models. © 2024 Wiley Periodicals LLC.

关键词： algorithm unrolling convex and non-convex optimization convolutional sparse model dictionary learning multi-layer convolutional sparse model recurrent neural network sparse coding sparse prior

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：