检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wang, Tao He, Xuming Cai, Yuanzheng Xiao, Guobao Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Information Science and Technology ShanghaiTech University Shanghai China College of Mathematics and Computer Science Fuzhou University NetDragon Fuzhou China

We present a context aware object detection method based on a retrieve-and-transform scene layout model. Given an input image, our approach first retrieves a coarse scene layout from a codebook of typical layout templates. In order to handle large layout variations, we use a variant of the spatial transformer network [1] to transform and refine the retrieved layout, resulting in a set of interpretable and semantically meaningful feature maps of object locations and scales. The above steps are implemented as a Layout Transfer Network which we integrate into Faster RCNN [2] to allow for joint reasoning of object detection and scene layout estimation. Extensive experiments on three public datasets verified that our approach provides consistent performance improvements to the state-of-the-art object detection baselines on a variety of challenging tasks in the traffic surveillance and the autonomous driving domains. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards explainable multi-party learning: A contrastive knowledge sharing framework

arXiv

引用

arXiv 2021年

作者： Gao, Yuan Li, Jiawei Gong, Maoguo Xie, Yu Qin, A.K. The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Shaanxi Province Xi'an710071 China The Key Laboratory of Computational Intelligence Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia

Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approaches are confronted with obstacles such as system heterogeneity, statistical heterogeneity, and incentive design. How to deal with these challenges and further improve the efficiency and performance of multi-party learning has become an urgent problem to be solved. In this paper, we propose a novel contrastive multi-party learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogize multiparty learning as a many-to-one knowledge sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

controller Synthesis of Signal Temporal Logical Tasks for Cyber-Physical Production Systems via Acyclic Decomposition

Controller Synthesis of Signal Temporal Logical Tasks for Cy...

引用

IEEE Conference on Decision and control

作者： Shuling Wang Shanying Zhu Cailian Chen Liang Xu Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China Institute of Artificial Intelligence Shanghai University Shanghai China

Modularization facilitates the adaptability of cyber-physical production systems (CPPSs) with a variety of collaborative tasks. Various production rules can be captured by signal temporal logic (STL) specifications imposed on interconnected multi-agent systems (MASs). In this paper, we focus on the controller synthesis of STL tasks for interconnected MASs to accomplish collaborative tasks in modular CPPSs. Firstly, a class of STL specifications characterizing tasks by the combination of fixed-time reachability and finite-time persistence tasks is proposed, which encompasses a large class of production specifications for the MAS. Secondly, the acyclic decomposition of the global STL formula is constructed to enable conflict-free collaborative tasks and unidirectional couplings between subsystems. By establishing the equivalence between the proposition and the state set of the MAS, necessary and sufficient conditions are respectively proposed for the satisfaction of reachability and persistence tasks. In addition, an algorithm is presented to synthesize controllers for the MAS with the global STL specification based on local controllers of subsystems. An illustrative example is given to show the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature fusion as a practical solution toward noncooperative iris recognition

Feature fusion as a practical solution toward noncooperative...

引用

International Conference on Information Fusion

作者： Nima Tajbakhsh Babak N. Araabi Hamid Soltanianzadeh Control & Intelligent Processing Center of Excellence School of Electrical & Computer Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit MI USA

In noncooperative Iris recognition one should deal with uncontrolled behavior of the subject as well as uncontrolled lighting conditions. That means imperfect focus, contrast, brightness, and orientation among the others. To cope with this situation we propose to take iris images at both near infrared (NIR) and visible light (VL) and use them simultaneously for recognition. In this paper, a novel approach for iris recognition is proposed so that extracted features of NIR and VL images are fused to improve the recognition rate. When the images do not have enough quality due to focus, contrast, etc., effects of feature fusion is more pronounced. This is the situation in UTIRIS database, which is used in our experiments. Experimental results show that the proposed approach, especially in small training samples, leads to a remarkable improvement on recognition rate compared with either NIR or VL recognition.

关键词： Iris Feature extraction Discrete cosine transforms image recognition Databases Training Humans

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

arXiv

引用

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Network with Residual Convolution for Leukocyte image Segmentation

An Encoder-Decoder Network with Residual Convolution for Leu...

引用

International Conference on Information Science and control Engineering (ICISCE)

作者： Yuanyuan Chen Shenghua Teng Zuoyong Li Fuquan Zhang Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China College of Electronics and Information Engineering Shandong University of Science and Technology Qingdao China Fuzhou Digital Healthcare Industry Technology Innovation Center Fuzhou China

The appearance analysis and counting of peripheral blood leukocytes can assist the diagnosis of blood diseases such as leukemia. Therefore, it is necessary to automatically extract leukocytes from blood smear images. In this paper, we propose an end-to-end peripheral blood leukocyte image segmentation method based on fully convolutional neural network, which can not only encode multi-scale contextual information, but also capture clear boundary information through decoding. Specifically, the proposed method first utilizes the context-aware feature encoder with residual convolutions to extract a set of multi-scale features. Then, a refinement module of parallel dilated convolutions with multiple dilation rates for expanding the receptive field of the feature maps is introduced to aggregate contextual information. Finally, clear prediction results are reconstructed by the context-aware feature decoder and skip connections. We demonstrate the effectiveness of the proposed method on two publicly available datasets.

关键词： Deep learning image segmentation Information science Aggregates Feature extraction Decoding Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A hybrid model based on stacking and multi-correction mechanisms for urban water demand prediction ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 16685-16690页

作者： Yang Lan Jingcheng Wang Miaoshun Bai Ibrahim Brahmia Haotian Xu Piao Hu Yuhao Long Yeming Zhang Dept. of Automation Shanghai Jiaotong University Key Laboratory of System Control and Information Processing Ministry of education of China Shanghai 200240 China. Autonomous Systems and Intelligent Control International Joint Research Center Xi’an Technological University Xi’an Shaanxi710021 China. Shanghai Municipal engineering Design Institute (Group) Co. Ltd.

Water demand prediction is the key link for the effective operation of urban intelligent water supply system. Since the non-linearity and complex variability of water consumption, it is difficult for traditional water demand prediction models to guarantee high accuracy for a long period. Different holiday types and even tiny changes in temperatures can affect urban water demand seriously. This paper proposes a Stacking-based hybrid model which integrates multi-correction mechanisms to address these problems. A better stacking model is proposed to minimize the generalization error. The stability and reliability of predictions are improved through the design of multi-correction mechanisms such as high temperature weather compensation feature, holiday-type correction model and water quantity fluctuation correction model. Comparing different models before and after stacking also before and after correcting, the prediction accuracy of the proposed hybrid model is much higher and the predictions are more stable and reliable.

关键词： Water supply system Prediction methods Hybrid models Stacking methods Multi-correction mechanisms Neural-network models Time-series analysis

来源：评论

学校读者我要写书评

暂无评论

Water Supply Prediction Based on Initialized Attention Residual Network

Water Supply Prediction Based on Initialized Attention Resid...

引用

第三十九届中国控制会议

作者： Yuhao Long Yeming Zhang Jingcheng Wang Miaoshun Bai Dept of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of China Shanghai Municipal Engineering Design Institute(Group)Co. Ltd Autonomous Systems and Intelligent Control International Joint Research Center Xi'an Technological University

Real-time and accurate water supply forecast is crucial for water supply control. However, most existing methods are likely affected by factors such as weather and holidays, which lead to a decline in the reliability of water supply *** this paper, we address a generic artificial neural network, Initialized Attention Residual Network(IARN), to tackle the time series prediction problem in water supply domain. Specifically, instead of continuing to use the recurrent neural network(RNN)in time-series tasks, we try to build a convolution neural network(CNN) to recede the disturb from other factors and get a more credible results. Experiments show that our method achieves state-of-the-art performance on several datasets in terms of accuracy,robustness and generalization ability. The source code of our method will available at https://***/SJTU-L-dd/IARN.

关键词： Neural networks Prediction methods Water supply Time-series analysis Attention module Residual network

来源：评论

学校读者我要写书评

暂无评论

Ascl: Accelerating Semi-Supervised Learning Via Contrastive Learning

SSRN

引用

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised Data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： image classification

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：