检索结果-内蒙古大学图书馆

Multi-scale Residual Alignment Transformer for Remote Sensing Image Change Detection

学校读者我要写书评

暂无评论

IEEE geoscience and Remote Sensing Letters 2025年

作者： Li, Lei Zhou, Xiao Yu, Xiaodong Gao, Bin Yan, Guogang Liu, Yidan Cui, Tingting Zhao, Guangyu Hu, Yuxin Chinese Academy of Sciences Key Laboratory of Technology in Geo-spatial Information Processing and Application System Key Laboratory of Target Cognition and Application Technology Aerospace Information Research Institute Beijing100094 China

Deep learning (DL) methods have shown great potential for remote sensing image change detection recently, but still suffer from several limitations. Within the identical semantic concept, significant but irrelevant changes in surface texture, color and spatial shifting of building objects resulted from variations in imaging physical factors, causes feature inconsistency of building objects in bitemporal sences. Conventional DL methods lack the capability to effectively distinguish real changes from irrelevant changes, leading to some false detections. This letter propose a novel framework, the multi-scale residual alignment transformer (AlignFormer), to mitigate the above issues. Specifically, inspired by deformable attention mechanism, we firstly design an adaptive feature alignment module (AFAM) to suppress the inconsistency of feature pairs, where the regions of building can be adaptively focused on and the spatial-temporal dependencies of relevant building objects in feature pairs effectively captured, via scheme of flexibly sampling keys/Values for each given Query. Besides, we utilize an extremely tiny Swin Transformer as the backbone of differencing-based framework for obtaining hierarchical features. Moreover, inspired by residual learning strategy, three AFAMs are integrated into the framework to form the multi-scale residual architecture for the coarse-to-fine alignment of the paired features. Experimental results confirm the superiority of our proposed method over several state-of-the-art algorithms. Our code will be released at https://***/lilei-aircas/AlignFormer_CD. © 2004-2012 IEEE.

关键词： Change detection

An ECG signal de-noising method combining the improved threshold function and ABC algorithm 3

学校读者我要写书评

暂无评论

An ECG signal de-noising method combining the improved thres...

2022 3rd International Conference on Computer information and Big Data applications, CIBDA 2022

作者： Deng, Yanrong Huang, Yanhu School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University Yulin537000 China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783800758760

Electrocardiogram (ECG) plays an imperative role in the clinical diagnosis of heart disease and heart abnormalities. In order to obtain the original ECG signal morphology, the wavelet threshold technique is usually used for ECG signal de-noising, in which threshold function and thresholds play very important role. In this paper, an improved threshold function with adjustable shape parameter was structured to improve the problems of the constant deviation in soft threshold function and the discontinuousness in hard threshold function. And then, an optimization strategy based on artificial bee colony algorithm with mean square error (MSE) as the objective function is embedded into the process of de-noising to quickly determine the optimal shape parameter and thresholds. Subsequently, a series of the simulation experiment are carried out by using two benchmark signals and real ECG signal with different noise levels. The signal-to-noise ratio (SNR) and the MSE after de-noising are used as evaluation index of the proposed method. The evaluation results demonstrate that the improved threshold function shows a better performance than the traditional threshold functions under different noise levels, and the proposed method is effective for the selections of the optimal shape parameter and thresholds in ECG signal de-noising. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Optimization

Robust Eigenvectors of Regular Simplex Tensors: Conjecture Proof

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Lei Geng, Xiurui Zhang, Lei The School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China University of the Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Science Beijing100190 China

The concept of tensor eigenpairs has received more researches in past decades. Recent works have paid attentions to a special class of symmetric tensors termed regular simplex tensors, which is constructed by equiangular tight frame of n + 1 vectors in n-dimensional space, and the robustness of eigenpairs was investigated. In the end of the literature, a conjecture was claimed that the robust eigenvectors of a regular simplex tensor are precisely the vectors in the frame. One later work theoretically proved that the case of n = 2 was true. In this paper, we proceed further and complete the proof for the above conjecture. Some promising directions are discussed in the end for future *** Codes 15A69, 90C26 © 2023, CC BY.

关键词： Tensors

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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)

Domain Knowledge Based Small Sample Ship Target Detection Method 3

学校读者我要写书评

暂无评论

Domain Knowledge Based Small Sample Ship Target Detection Me...

3rd China International SAR Symposium, CISS 2022

作者： Zhou, Jianing Li, Zheng Yang, Wei Zou, Fei Wang, Hui BeiHang University School of Electronic and Information Engineering Beijing China Aerospace Information Research Institute Beijing China Chinese Academy of Sciences Key Laboratory of Technology in Geospatial Information Processing and Application System Beijing China Beijing Institute of Remote Sensing Information Beijing China Shanghai Institute of Satellite Engineering Shanghai China

ISBN: (数字)9798350398717

ISBN: (纸本)9798350398717

Synthetic Aperture Radar (SAR) is widely used in ship target detection because of its ability to operate under various weather conditions. However, some target images are difficult to obtain and label, resulting in a small sample size, which limits the development of target detection. Aiming at the problem of ship target detection in small sample SAR images, domain knowledge is used to revise and enhance the basic model in this paper. Firstly, a lightweight convolutional neural network model more suitable for small-sample SAR image ship target classification is proposed, involving target pixel and aspect ratio as domain knowledge to correct the classification results. Then, for ship target detection in SAR images, the acquisition method of scale class domain knowledge is improved. Moreover, texture-related domain knowledge based on the gray level co-occurrence matrix is extracted and used as classification features for the model to revise the model. Finally, Marine Targets Classification Dataset (MTCD) and Marine Targets Detection Dataset (MTDD) are briefly introduced and adjusted to meet the requirements of this research through screening and modification. The test results on balanced MTDD and small-sample datasets demonstrate the effectiveness of domain knowledge in improving network performance. © 2022 IEEE.

关键词： Deep learning