检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhussip, Magauiya Koshelev, Iaroslav Lefkimmiatis, Stamatis MTS AI AI Foundation and Algorithm Lab

Diffusion Probabilistic Models (DPMs) have been recently utilized to deal with various blind image restoration (IR) tasks, where they have demonstrated outstanding performance in terms of perceptual quality. However, the task-specific nature of existing solutions and the excessive computational costs related to their training, make such models impractical and challenging to use for different IR tasks than those that were initially trained for. This hinders their wider adoption, especially by those who lack access to powerful computational resources and vast amount of training data. In this work we aim to address the above issues and enable the successful adoption of DPMs in practical IR-related applications. Towards this goal, we propose a modular diffusion probabilistic IR framework (DP-IR), which allows us to combine the performance benefits of existing pre-trained state-of-the-art IR networks and generative DPMs, while it requires only the additional training of a relatively small module (0.7M params) related to the particular IR task of interest. Moreover, the architecture of the proposed framework allows for a sampling strategy that leads to at least four times reduction of neural function evaluations without suffering any performance loss, while it can also be combined with existing acceleration techniques such as DDIM. We evaluate our model on four benchmarks for the tasks of burst JDD-SR, dynamic scene deblurring, and superresolution. Our method outperforms existing approaches in terms of perceptual quality while it retains a competitive performance with respect to fidelity metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Joint BS-RIS-User Association and Deployment Design for Multi-RIS-Aided Wireless Networks

引用

IEEE COMMUNICATIONS LETTERS 2024年第9期28卷 2181-2185页

作者： Wang, Yibo Zhang, Yang Ren, Yaxin Pang, Lihua Chen, Yijian Li, Jiandong Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xian Univ Sci & Technol Xian Key Lab Network Convergence Commun Xian 710054 Peoples R China ZTE Corp Algorithm Dept Shenzhen 518057 Peoples R China

In this letter, we consider a multi-reconfigurable intelligent surface(RIS)-assisted multi-cell communication system in which we jointly optimize the base station (BS)-RIS-user association and RIS deployment locations to maximize the ergodic capacity. In order to derive deterministic approximate expressions for the ergodic capacity, active and passive beamforming are first optimized to maximize the signal power of the relevant path. Then, we propose a two-level nested algorithm to address this mixed-integer nonlinear programming (MINLP) problem. Finally, the effectiveness of the proposed algorithm is validated through numerical simulations.

关键词： Interference Array signal processing Signal to noise ratio Vectors Rician channels Reflection Rayleigh channels Reconfigurable intelligent surface (RIS) BS-RIS-user association RIS deployment ergodic capacity

来源：评论

学校读者我要写书评

暂无评论

A flare removal network for night vision perception: Resistant to the interference of complex light

引用

IET IMAGE PROCESSING 2024年第12期18卷 3192-3205页

作者： Liu, Yan Huang, Guan Qi, Wenting Li, Yujie Zhengzhou Univ Light Ind Sch Comp Sci & Technol Zhengzhou Peoples R China Guilin Univ Elect Technol Sch Artificial Intelligence Guangxi Coll & Univ Key Lab AI Algorithm Engn Guilin 541004 Peoples R China

The high-precision visual perception results are easily affected by the lens flare issue when the image sensor is facing to strong light. The existing flare removal methods have poor robustness when confronted with flare interference caused by complex nighttime lighting, which has to preserve natural light source information. A simulated dataset for the removal of night flares is created to solve the problem of collecting complete paired training data, and night flare removal network (NFR-Net) is proposed to remove the interference caused by various light disturbances at night. The light source extraction module is introduced to retain light source information realistically and effectively in night vision scenes. Extensive experimental results demonstrate that the proposed method is superior to the existing related methods in the various complex night vision scenes. The proposed NFR-Net can enhance visual perception of nighttime images significantly and improve the performance of night vision tasks. Aiming at the problem of strong flare interference in the image captured when the sensor points at a strong light source. This paper proposes a night flare removal network trained on synthetic data which can remove a variety of flare interference while reasonably retaining the light source information. Compared with the existing methods, this method achieves better visual perception and makes up for the lack of methods in the field of night flare removal. image

关键词： computer vision convolutional neural nets image enhancement

来源：评论

学校读者我要写书评

暂无评论

Relative controllability of neutral delay differential equations on quaternion skew field

引用

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION 2025年 142卷

作者： Fu, Teng Wang, Jinrong Guizhou Univ Dept Math Guiyang 550025 Guizhou Peoples R China Guizhou Univ Supercomp Algorithm & Applicat Lab Guiyang 550025 Guizhou Peoples R China Guizhou Univ Guian Sci Innovat Co Guiyang 550025 Guizhou Peoples R China

The research focuses on relative controllability of neutral delay differential equations on quaternion skew field (NDQDEs). First, we derive the representation of solutions for NDQDEs by quaternion determining equations and neutral delay quaternion matrix function. Then, the Gram criterion of relative controllability for NDQDEs in different cases is given with the help of the representation of solutions. By the analogy of Cayley-Hamilton theorem, the rank criterion of relative controllability is obtained. The complete characterization of quaternion control functions is obtained by a special right inverse matrix and shifted Legendre polynomials. Besides, we discuss the relative controllability of weakly nonlinear NDQDEs. Finally, we provide examples to verify the theoretical results.

关键词： Neutral delay Quaternion differential equations Solution Relative controllability

来源：评论

学校读者我要写书评

暂无评论

Block-Dependent Partition Decision for Fast Intra Coding of VVC

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 277-289页

作者： Peng, Zixiao Shen, Liquan Ding, Qing Dong, Xinchao Zheng, Linru Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Beihang Univ Sch Commun & Informat Engn Beijing 100191 Peoples R China Agora Lab Inc Video Algorithm Santa Clara CA 95054 USA

Aiming at accelerating the intra coding process of versatile video coding (VVC), previous efforts are made to predict the quad-tree plus multi-type tree (QTMT) partition structure, in which the prediction is modeled as a classification procedure. The existing deep learning-based methods usually represent the block partition as a structural output and utilize a single convolutional neural network (CNN) for the prediction of all blocks. However, they take different blocks equally, i.e., one-for-all, which ignores that the blocks with different complexity of partition structures are unevenly distributed and have different prediction difficulties. To address this problem, we propose a novel block-dependent partition decision (BDPD) framework to adaptively process different blocks by networks with different capacities. Specifically, we design a partition homogeneity map (PHM) to represent the QTMT-based block partition, which combines different partition directions to effectively reflect the complexity of the partition structure. On this basis, we propose a class-based prediction to distinguish blocks with different complexity of the partition structure and adopt appropriate FCN models to predict PHM, incorporating block classification and PHM prediction. The blocks are classified into different classes according to their coarse texture and neighboring PHMs. Then different fully convolutional network (FCN) models are utilized to predict PHM for different classes. The FCN models with different capacities are trained in the corresponding class, respectively, which achieves higher performance with less computation on the extremely unbalanced natural video. Finally, an adaptive partition decision based on predicted PHMs is adopted to conduct partition decisions for a better trade-off between rate-distortion performance and encoding complexity. Experimental results show that our approach achieves 45.7%similar to 74.5% encoding complexity reduction with 0.78%similar to 3.38% B

关键词： Versatile video coding intra coding coding unit partition quadtree plus multi-type tree complexity reduction deep learning

来源：评论

学校读者我要写书评

暂无评论

An average-compress algorithm for the sample mean problem under dynamic time warping

引用

JOURNAL OF GLOBAL OPTIMIZATION 2023年第4期86卷 885-903页

作者： Jain, Brijnesh Froese, Vincent Schultz, David OTH Regensburg Dept Comp Sci & Math Regensburg Germany TU Berlin Fac 4 Algorithm & Computat Complex Berlin Germany TU Berlin Fac 4 Distributed Artificial Intelligence Lab Berlin Germany

Computing a sample mean of time series under dynamic time warping is NP-hard. Consequently, there is an ongoing research effort to devise efficient heuristics. The majority of heuristics have been developed for the constrained sample mean problem that assumes a solution of predefined length. In contrast, research on the unconstrained sample mean problem is underdeveloped. In this article, we propose a generic average-compress (AC) algorithm to address the unconstrained problem. The algorithm alternates between averaging (A-step) and compression (C-step). The A-step takes an initial guess as input and returns an approximation of a sample mean. Then the C-step reduces the length of the approximate solution. The compressed approximation serves as initial guess of the A-step in the next iteration. The purpose of the C-step is to direct the algorithm to more promising solutions of shorter length. The proposed algorithm is generic in the sense that any averaging and any compression method can be used. Experimental results show that the AC algorithm substantially outperforms current state-of-the-art algorithms for time series averaging.

关键词： Time series averaging Frechet function Heuristic Nonconvex optimization

来源：评论

学校读者我要写书评

暂无评论

Black-Box Testing and Auditing of Bias in ADM Systems

引用

MINDS AND MACHINES 2024年第2期34卷 15-15页

作者： Krafft, Tobias D. Hauer, Marc P. Zweig, Katharina TU Kaiserslautern Algorithm Accountabil Lab Gottlieb Daimler Str D-67655 Kaiserslautern Germany

For years, the number of opaque algorithmic decision-making systems (ADM systems) with a large impact on society has been increasing: e.g., systems that compute decisions about future recidivism of criminals, credit worthiness, or the many small decision computing systems within social networks that create rankings, provide recommendations, or filter content. Concerns that such a system makes biased decisions can be difficult to investigate: be it by people affected, NGOs, stakeholders, governmental testing and auditing authorities, or other external parties. Scientific testing and auditing literature rarely focuses on the specific needs for such investigations and suffers from ambiguous terminologies. With this paper, we aim to support this investigation process by collecting, explaining, and categorizing methods of testing for bias, which are applicable to black-box systems, given that inputs and respective outputs can be observed. For this purpose, we provide a taxonomy that can be used to select suitable test methods adapted to the respective situation. This taxonomy takes multiple aspects into account, for example the effort to implement a given test method, its technical requirement (such as the need of ground truth) and social constraints of the investigation, e.g., the protection of business secrets. Furthermore, we analyze which test method can be used in the context of which black box audit concept. It turns out that various factors, such as the type of black box audit or the lack of an oracle, may limit the selection of applicable tests. With the help of this paper, people or organizations who want to test an ADM system for bias can identify which test methods and auditing concepts are applicable and what implications they entail.

关键词： Testing Auditing Bias Black box Artificial intelligence Machine learning Automated decision-making

来源：评论

学校读者我要写书评

暂无评论

Bayesian Nonparametric Classification for Incomplete Data With a High Missing Rate: an Application to Semiconductor Manufacturing Data

引用

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 2023年第2期36卷 170-179页

作者： Park, Sewon Lee, Kyeongwon Jeong, Da-Eun Ko, Heung-Kook Lee, Jaeyong Samsung SDS Secur Algorithm Lab Seoul 06765 South Korea Seoul Natl Univ Dept Stat Seoul 08826 South Korea Samsung Elect Mfg Qual & Reliabil Grp Yongin 17113 Gyeonggi South Korea

During the semiconductor manufacturing process, predicting the yield of the semiconductor is an important problem. Early detection of defective product production in the manufacturing process can save huge production cost. The data generated from the semiconductor manufacturing process have characteristics of non-normal distributions, random missing patterns and high missing rate, which complicate the prediction of the yield. We propose the Dirichlet Process - Naive Bayes model (DPNB) that can simultaneously impute missing values and address classification problems. Since the DPNB is based on the infinite Gaussian mixture model, it can estimate complex data distributions and make predictions for missing datasets with some missing patterns due to nice properties of the Gaussian distribution. The DPNB also performs well for high missing rates since it uses all information of observed components. Experiments on various real datasets including semiconductor manufacturing data show that the DPNB has better performance than state-of-the-art methods in terms of predicting missing values and target variables as percentage of missing values increases.

关键词： Data models Statistics Semiconductor device manufacture Semiconductor device modeling Gaussian mixture model Gaussian distribution Random forests Missing data imputation classification semiconductor defects yield estimation

来源：评论

学校读者我要写书评

暂无评论

Federated Boolean Neural Networks Learning 8

Federated Boolean Neural Networks Learning

引用

8th IEEE International Conference on Fog and Mobile Edge Computing (FMEC)

作者： Leconte, Louis Van Minh Nguyen Moulines, Eric Sorbonne Univ LISITE Paris France Huawei Technol Math & Algorithm Sci Lab Paris France Ecole Polytech CMAP Paris France

ISBN: (纸本)9798350316971

In this paper, we propose a new centralized Federated Learning (FL) for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, federated learning faces the increasingly difficult task of scaling communication over large wireless networks with limited bandwidth. Moreover, this distributed training paradigm requires clients to perform intensive computations for multiple iterations, which may exceed the capacity of a typical edge device with limited processing power, storage capacity, and energy budget. Therefore, practical deployment of FL requires a balance between energy efficiency due to resource constraints and latency due to bandwidth constraints. In this work, we overcome both constraints by integrating low-precision arithmetic on clients and exchanging only highly compressed vectors during training. Experimental results show that the proposed algorithms FedBool and MajBool perform better than current methods on standard image classification tasks.

关键词： federated learning binary neural networks Boolean logic propagation

来源：评论

学校读者我要写书评

暂无评论

Constant Weight Codes With Gabor Dictionaries and Bayesian Decoding for Massive Random Access

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第5期22卷 2917-2931页

作者： Agostini, Patrick Utkovski, Zoran Decurninge, Alexis Guillaud, Maxime Stanczak, Slawomir Fraunhofer Heinrich Hertz Inst Dept Wireless Commun & Networks D-10587 Berlin Germany Huawei Technol France Paris Res Ctr Math & Algorithm Sci Lab F-92100 Boulogne Billancourt France

This paper considers a general framework for massive random access based on sparse superposition coding. We provide guidelines for the code design and propose the use of constant-weight codes in combination with a dictionary design based on Gabor frames. The decoder applies an extension of approximate message passing (AMP) by iteratively exchanging soft information between an AMP module that accounts for the dictionary structure, and a second inference module that utilizes the structure of the involved constant-weight code. We apply the encoding structure to (i) the unsourced random access setting, where all users employ a common dictionary, and (ii) to the "sourced" random access setting with user-specific dictionaries. When applied to a fading scenario, the communication scheme essentially operates non-coherently, as channel state information is required neither at the transmitter nor at the receiver. We observe that in regimes of practical interest, the proposed scheme compares favorably with state-of-the art schemes, in terms of the (per-user) energy-per-bit requirement, as well as the number of active users that can be simultaneously accommodated in the system. Importantly, this is achieved with a considerably smaller size of the transmitted codewords, potentially yielding lower latency and bandwidth occupancy, as well as lower implementation complexity.

关键词： Massive random access IoT unsourced random access Bayesian inference message passing

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：