检索结果-内蒙古大学图书馆

A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with applications in Tomographic SAR Imaging

arXiv

引用

arXiv 2022年

作者： Shi, Ruizhe Zhang, Zhe Qiu, Xiaolan Ding, Chibiao School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China Suzhou Aerospace Information Research Institute Suzhou Key Laboratory of Intelligent Aerospace Big Data Application Technology Jiangsu Suzhou215123 China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing100190 China

This paper presents a novel efficient method for gridless line spectrum estimation problem with single snapshot, namely the gradient descent least squares (GDLS) method. Conventional single snapshot (a.k.a. single measure vector or SMV) line spectrum estimation methods either rely on smoothing techniques that sacrifice the array aperture, or adopt the sparsity constraint and utilize compressed sensing (CS) method by defining prior grids and resulting in the off-grid problem. Recently emerged atomic norm minimization (ANM) methods achieved gridless SMV line spectrum estimation, but its computational complexity is extremely high;thus it is practically infeasible in real applications with large problem scales. Our proposed GDLS method reformulates the line spectrum estimations problem into a least squares (LS) estimation problem and solves the corresponding objective function via gradient descent algorithm in an iterative fashion with efficiency. The convergence guarantee, computational complexity, as well as performance analysis are discussed in this paper. Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e.g., CS and ANM, in terms of estimation performances. It can completely avoid the off-grid problem, and its computational complexity is significantly lower than ANM. Our method has been tested in tomographic SAR (TomoSAR) imaging applications via simulated and real experiment data. Results show great potential of the proposed method in terms of better cloud point performance and eliminating the gridding effect. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

arXiv

引用

arXiv 2022年

作者： Zhao, Youpeng Zhao, Jian Hu, Xunhan Zhou, Wengang Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

arXiv

引用

arXiv 2022年

作者： Li, Qing Zhou, Wengang Lu, Zhenbo Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230000 China

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks. However, they still suffer two nontrivial obstacles, i.e., low sample efficiency and overestimation bias. To this end, we propose Simultaneous Double Q-learning with Conservative Advantage Learning (SDQ-CAL). Our SDQ-CAL boosts the Double Q-learning for off-policy actor-critic RL based on a modification of the Bellman optimality operator with Advantage Learning. Specifically, SDQ-CAL improves sample efficiency by modifying the reward to facilitate the distinction from experience between the optimal actions and the others. Besides, it mitigates the overestimation issue by updating a pair of critics simultaneously upon double estimators. Extensive experiments reveal that our algorithm realizes less biased value estimation and achieves state-of-the-art performance in a range of continuous control benchmark tasks. We release the source code of our method at: https://***/LQNew/SDQ-CAL. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment

arXiv

引用

arXiv 2024年

作者： Fu, Jun Zhou, Wei Jiang, Qiuping Liu, Hantao Zhai, Guangtao The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom The School of Information Science and Engineering Ningbo University Ningbo315211 China The Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China

Recently, textual prompt tuning has shown inspirational performance in adapting Contrastive Language-Image Pre-training (CLIP) models to natural image quality assessment. However, such uni-modal prompt learning method only tunes the language branch of CLIP models. This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images. In addition, the consistency between AGIs and user input text prompts, which correlates with the perceptual quality of AGIs, is not investigated to guide AGIQA. In this letter, we propose vision-language consistency guided multi-modal prompt learning for blind AGIQA, dubbed CLIP-AGIQA. Specifically, we introduce learnable textual and visual prompts in language and vision branches of CLIP models, respectively. Moreover, we design a text-to-image alignment quality prediction task, whose learned vision-language consistency knowledge is used to guide the optimization of the above multi-modal prompts. Experimental results on two public AGIQA datasets demonstrate that the proposed method outperforms state-of-the-art quality assessment models. The source code is available at https://***/JunFu1995/CLIP-AGIQA. © 2024, CC BY-NC-ND.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

AF2S: An Anchor-Free Two-Stage Tracker Based on a Strong SiamFC Baseline 16th

AF2S: An Anchor-Free Two-Stage Tracker Based on a Strong Sia...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： He, Anfeng Wang, Guangting Luo, Chong Tian, Xinmei Zeng, Wenjun CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China Microsoft Research Asia Beijing China

ISBN: (纸本)9783030682378

Siamese network based trackers have become a mainstream in visual object tracking. Recently, several high-performance multi-stage trackers have been proposed and some of them adopt SiamRPN for the first-stage region proposal. We argue that an anchor-based region proposal network is not necessary for the tracking task, as a tracker has a strong prior about the location and size of the target. In this paper, we propose a two-stage visual tracker which uses SiamFC for region proposal. SiamFC defines a bounding box by its center, which is a typical anchor-free (AF) network, so we dub our tracker AF2S. As the model size of SiamFC is only about 1/10 that of SiamRPN, AF2S results in a significantly lighter model than its SiamRPN-based counterparts. In the design of AF2S, we first build a strong AlexNet-based SiamFC baseline which improves the AUC on OTB-100 from 0.582 to 0.665. Further, we propose a position-sensitive convolutional layer which can be stacked after SiamFC backbone to increase the robustness of proposals without losing localization precision. Finally, a relation network is used for box refinement. Experimental results show that AF2S achieves the best performance on OTB-100 and VOT-18 among the state-of-the-art trackers which use AlexNet as backbone. On LaSOT-test, AF2S achieves an AUC of 0.480, which is among the first-tier performance even when trackers with more powerful backbone and much larger model size are considered. © 2020, Springer Nature Switzerland AG.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Quantum-behaved PSO-based Lyapunov control of closed quantum systems

Quantum-behaved PSO-based Lyapunov control of closed quantum...

引用

第40届中国控制会议

作者： Song Liu Sen Kuang Department of Automation University of Science and Technology of China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China

A Lyapunov-based control scheme is presented to drive closed quantum systems into any target eigenstate with as high population as possible by the quantum-behaved particle swarm optimization（PSO） algorithm. Based on a Lyapunov function with a Hermitian operator to be constructed, a control law with the unknown parameters contained in the Hermitian operator is designed. To achieve high-population state transfer to the target state, we first initialize those unknown parameters by choosing a path to the target state in its energy-level connectivity graph and setting their values along the path. Then, a set of optimal parameters is found by the quantum-behaved PSO algorithm. Finally, numerical simulation experiments are performed on a five-level quantum system and a four-qubit system to demonstrate the effectiveness of the control scheme in this paper.

关键词： Quantum systems Lyapunov control quantum-behaved PSO algorithm energy-level connectivity graph high-population transfer

来源：评论

学校读者我要写书评

暂无评论

Single Channel CSAR Moving Target Detection Algorithm Based on Low-rank Sparse Decomposition

Single Channel CSAR Moving Target Detection Algorithm Based ...

引用

IEEE International Conference on Radar

作者： Zhiguo Zhang Wenjie Shen Xiaoyang Yue Yun Lin Wen Hong Key Laboratory of Technology in Geospatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Radar Monitoring Technology Laboratory School of Information Science and Technology North China University of Technology Beijing China

ISBN: (纸本)9781665468893

With the goal of detecting moving targets, this paper proposes a new single channel Circular Synthetic Aperture Radar (CSAR) moving targets detection algorithm based on Low-rank Sparse Decomposition (LRSD). This algorithm utilizes the correlation among overlap subaperture logarithmic amplitude image sequences, the static clutter is regarded as low-rank component and the moving targets is considered as sparse component. Then, the background image sequence (without moving target) and the foreground image sequence (moving targets) can be extracted by the LRSD. Considering the unknown foreground image distribution, this paper proposes a Local Dynamic Threshold based on Otsu (LDTO) method independent of image distribution to detect moving targets. Finally, the experiment on the X-band airborne Gotcha Data demonstrates the effectiveness of the proposed algorithm.

关键词： Correlation Heuristic algorithms Airborne radar Radar detection Object detection Detectors Radar imaging

来源：评论

学校读者我要写书评

暂无评论

An adaptive Enhanced Imaging Method for Multi-aspect SAR

An adaptive Enhanced Imaging Method for Multi-aspect SAR

引用

IEEE International Conference on Radar

作者： Fei Teng Yun Lin Xiaoyang Yue Shanshan Feng Wen Hong Key Laboratory of Technology in Geospatial Information Processing and Application System Chinese Academy of Sciences Aerospace Information Research Institute Beijing China School of Electronic Information Engineering North China University of Technology Beijing China

ISBN: (纸本)9781665468893

Compared with traditional SAR working modes, multi-aspect SAR can provide images with higher resolution and signal-to-noise ratio (SNR) due to its larger synthetic aperture. However, the SNR does not increase with the increase of the aperture length. This is because the scattering is no longer isotropic as traditional SAR when the viewing angle is large. In this paper, an adaptive enhanced imaging method for multi-aspect SAR is proposed. The resolution and the SNR are maximized by scattering analysis performed simultaneously with imaging. In the process of image generation, the scattering characteristic is analyzed and all targets are divided into two categories: isotropic and anisotropic. Then different image formation strategies are used for isotropic and anisotropic target. A C-band circular SAR data is used to validate our method.

关键词： Image resolution C-band Scattering Imaging Radar scattering Radar imaging Apertures

来源：评论

学校读者我要写书评

暂无评论

Research on Integrated Deployment Method of Digital Earth Thematic application Model 1

Research on Integrated Deployment Method of Digital Earth Th...

引用

1st China Digital Earth Conference, CDEC 2019

作者： Danpu, Zhao Xianqing, Tai Zhijie, Ma Key Laboratory of Technology in Geospatial Information Processing and Application System Institute of Elec-tronics Chinese Academy of Sciences Beijing100190 China Research Center of Intelligent City and Intelligent Transportation CAS R and D Center for Internet of Things Wuxi214135 China

Nowadays, the digital earth not only relates to the technologies of surveying and mapping geography, but also includes the analysis and cross-application of various scientific data related to geographic information. It requires a computing environment and management for the corresponding thematic application models which supports the online analysis on the digital earth. So we proposed an integrated deployment method for digital earth thematic application models based on container cloud, which provides a flexible and scalable information integration and analysis architecture for digital earth. Firstly, a Docker image building module is designed to facilitate the user to quickly build the application model into a image. Then the Docker technology is used to implement the containerization of the application model to provide a stable running environment for the application model. Finally, the Kubernetes is used to dynamically manage the cluster resources to realize rapid expansion of computing resources. In addition, the HDFS is deployed, and the image files and various scientific data respectively store with Hbase and Apache file systems. It can ensure the read and write speed of the application model and the related data and log files. It also used zabbix framework to manage the monitoring index of the container cloud cluster to ensure the execution effect of the application model. Through the tests of typical application model, it is verified that the method can integrated deploy and apply the cross-domain, hetero-architecture, multi-version and multi-class application models on the digital earth. © Published under licence by IOP Publishing Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Lin, Jianxin Pang, Yingxue Xia, Yingce Chen, Zhibo Luo, Jiebo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China University of Rochester Rochester United States

ISBN: (数字)9783030585488

ISBN: (纸本)9783030585471

An unsupervised image-to-image translation (UI2I) task deals with learning a mapping between two domains without paired images. While existing UI2I methods usually require numerous unpaired images from different domains for training, there are many scenarios where training data is quite limited. In this paper, we argue that even if each domain contains a single image, UI2I can still be achieved. To this end, we propose TuiGAN, a generative model that is trained on only two unpaired images and amounts to one-shot unsupervised learning. With TuiGAN, an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details. We conduct extensive experiments to verify that our versatile method can outperform strong baselines on a wide variety of UI2I tasks. Moreover, TuiGAN is capable of achieving comparable performance with the state-of-the-art UI2I models trained with sufficient data. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

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

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

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：