检索结果-内蒙古大学图书馆

TechRxiv 2021年

作者： Song, Kaiqiang Jiang, Jie School of Instrumentation and Optoelectronic Engineering Key Laboratory of Precision Opto-mechatronics Technology Ministry of Education Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing100191 China

While deep learning-based methods have gained popularity and have made remarkable progress in remote sensing (RS) image change detection (CD), the limited amount of available data hinders the performance of most supervised methods. The CD networks transferred or derived from other fields can be fronted with a weak generalization capability. Developing a universal benchmark for performance evaluations based on the available datasets is urgent. To address these problems, we proposed a lightweight network, termed 3M-CDNet, which only requires about 3.12 M parameters. The lighter the network, the easier it is to train and alleviate overfitting the limited amount of data, resulting in a better generalization capability. 3M-CDNet has a flexible modular design that achieves performance improvements by incorporating plug-and-play modules. 3M-CDNet gains accuracy improvements in two ways: (1) the application of deformable convolutions (DConv) in the backbone network to gain a good geometric transformation modeling capacity for CD and (2) the application of an effective two-level feature fusion strategy to enhance the feature representation capacity. 3M-CDNet gains a good generalization capacity by incorporating effective "tricks" to alleviate overfitting, in which online data augmentation (Online DA) is applied to increase the diversity of the training samples, and Dropout regularization is applied in the classifier. Extensive ablation studies have proved the effectiveness of the core components. Experiment results suggest that 3M-CDNet outperforms state-of-the-art methods on several optical RS datasets and serves as a new universal benchmark. Specifically, 3M-CDNet achieves the best F1-score, i.e., LEVIR-CD (0.9161), Season-Varying (0.9473), and DSIFN (0.7031). © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

MetaGCD: Learning to Continually Learn in Generalized Category Discovery

arXiv

引用

arXiv 2023年

作者： Wu, Yanan Chi, Zhixiang Wang, Yang Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Electrical and Computer Engineering University of Toronto TorontoM5G1V7 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method. Our code is available at https://***/ynanwu/MetaGCD. © 2023, CC0.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Medical Image Fusion Method Incorporating an Adaptive Attention Mechanism

A Multimodal Medical Image Fusion Method Incorporating an Ad...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yingxian Zhang Yushui Geng Hu Liang Hai Zhong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China Department of Radiology The Second Hospital of Shandong University Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Multimodal medical image fusion technology provides more comprehensive and accurate image support for clinical diagnosis and treatment by integrating complementary information from different imaging modalities. Aiming at the problem that existing methods are still insufficient in detail feature extraction and inter-modal information fusion, this paper proposes a multimodal medical image fusion method combined with an adaptive attention mechanism. First, we design the Grouped Receptive Field Attentional Convolution (GRFAConv) to solve the problem of insufficient detail feature extraction capability. With the multi-head receptive field adaptive weighting strategy of grouped convolution, the range and weight of the receptive field of the convolution kernel can be adaptively adjusted according to the different demands of local and global features of the image to improve the effect of detail retention. Second, for the problem of information fusion between different modalities, we introduce an improved CBAM attention module in the feature fusion process, which adaptively selects and enhances the features in the key regions through the channel attention and spatial attention mechanisms, which greatly improves the clarity of the fused image details and the accuracy of the information expression in the key regions. Furthermore, experimental results on several medical image datasets show that the algorithm proposed in this paper can generate relatively high-quality fused images. It not only enriches the detailed features of the image, but also achieves significant advantages in several evaluation metrics.

关键词： Measurement Attention mechanisms Accuracy Convolution Federated learning Feature extraction Clinical diagnosis Kernel Medical diagnostic imaging Image fusion

来源：评论

学校读者我要写书评

暂无评论

Pareto-aware Neural Architecture Generation for Diverse Computational Budgets

arXiv

引用

arXiv 2022年

作者： Guo, Yong Chen, Yaofo Zheng, Yin Chen, Qi Zhao, Peilin Chen, Jian Huang, Junzhou Tan, Mingkui The School of Software Engineering South China University of Technology China Max Planck Institute for Informatics Germany The Weixin Group Tencent China The School of Computer Science The University of Adelaide Australia Tencent AI Lab Tencent China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China

Designing feasible and effective architectures under diverse computational budgets, incurred by different applications/devices, is essential for deploying deep models in real-world applications. To achieve this goal, existing methods often perform an independent architecture search process for each target budget, which is very inefficient yet unnecessary. More critically, these independent search processes cannot share their learned knowledge (i.e., the distribution of good architectures) with each other and thus often result in limited search results. To address these issues, we propose a Pareto-aware Neural Architecture Generator (PNAG) which only needs to be trained once and dynamically produces the Pareto optimal architecture for any given budget via inference. To train our PNAG, we learn the whole Pareto frontier by jointly finding multiple Pareto optimal architectures under diverse budgets. Such a joint search algorithm not only greatly reduces the overall search cost but also improves the search results. Extensive experiments on three hardware platforms (i.e., mobile device, CPU, and GPU) show the superiority of our method over existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

Microstructure, Mechanism and Performance of Tungsten Coating Electrodeposited in Na2wo4–Wo3–Napo3–Y2o3 Molten Salt

SSRN

引用

SSRN 2022年

作者： Xi, Xiaoli Qin, Wenxuan Zhang, Liwen Nie, Zuoren Collaborative Innovation Center of Capital Resource-Recycling Material Technology Beijing University of Technology Beijing100124 China Key Laboratory of Advanced Functional Materials Ministry of Education Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China National Engineering Laboratory for Industrial Big-data Application Technology Beijing University of Technology Beijing100124 China

In this paper, smooth tungsten coatings with fine grains were prepared by constant direct current electrodeposition in different molten salt. The X–ray diffraction, scanning electron microscopy and laser scanning confocal microscope were used to characterize the microstructure and micromorphology of tungsten coatings. The micromorphology and surface roughness of tungsten coatings are significantly influenced by the cathodic overpotential. The cathodic overpotential can be modified by the addition of NaPO3 and Y2O3 to influence the coating surface quality. When 3.0 mol% Y2O3 was added to the Na2WO4–WO3–NaPO3 molten salt, the coating has the finest average grains size of 9.86 µm. What’s more, with the Y2O3 concentration increasing, the Ra of the coatings decreases. It is noteworthy that the synergistic addition of NaPO3 and Y2O3 results in superior surface quality. The microhardness and thermal shock resistance of the coatings are improved due to grain refinement. The electroreduction mechanism was explored by electrochemical testing and thermodynamic calculations. The results indicated that the electroreduction of tungsten ions is W(VI)→W(IV)→W, and differences in redox potential and overpotential of tungsten ions in different molten salt were observed by electrochemical tests. © 2022, The Authors. All rights reserved.

关键词： Electrodeposition

来源：评论

学校读者我要写书评

暂无评论

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification 28

A Two-phase Prototypical Network Model for Incremental Few-s...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Ren, Haopeng Cai, Yi Chen, Xiaofeng Wang, Guohua Li, Qing School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China Department of Computing The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781952148279

Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emergence of novel relations in an open environment. To incrementally recognize the novel relations, current two solutions (i.e, re-training and lifelong learning) are designed but suffer from the lack of large-scale labeled data for novel relations. Meanwhile, prototypical network enjoys better performance on both fields of deep supervised learning and few-shot learning. However, it still suffers from the incompatible feature embedding problem when the novel relations come in. Motivated by them, we propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances meanwhile without catastrophic forgetting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DBA_SSD A Novel End-to-End Object Detection Using Deep Attention Module for Helping Smart Device with Vegetable and Fruit Leaf Plant Disease Detection

Research Square

引用

Research Square 2021年

作者： Wang, Jun Yang, Jing Yu, Liya Dong, Hao Wang, Yifan School of Mechanical Engineering Guizhou University Guiyang550025 China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang550025 China Key Laboratory of Advanced Manufacturing Technology Ministry of Education Guizhou University Guiyang550025 China

In response to the difficulty of detecting and classifying pests and vegetable and fruit leaves with pests and diseases, this study proposes a novel vegetable and fruit leaf pest detection method called deep block attention SSD (DBA_SSD) for the identification of pests and diseases and classification of the degree of pests and diseases of vegetable and fruit leaves. We propose three vegetable and fruit leaf pest detection methods, namely, squeeze-and excitation SSD (Se_SSD), DB_SSD, and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected vegetable and fruit disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms. © 2021, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the Wild

arXiv

引用

arXiv 2022年

作者： Huang, Sheng Tang, Wenhao Huang, Guixin Huangfu, Luwen Yang, Dan Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing400044 China The School of Big Data and Software Engineering Chongqing University Chonqqing 400044 China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA92182 United States

Automatic image-based pavement distress detection and recognition are vital for pavement maintenance and management. However, existing deep learning-based methods largely omit the specific characteristics of pavement images, such as high image resolution and low distress area ratio, and are not end-to-end trainable. In this paper, we present a series of simple yet effective end-to-end deep learning approaches named Weakly Supervised Patch Label Inference Networks (WSPLIN) for efficiently addressing these tasks under various application settings. WSPLIN transforms the fully supervised pavement image classification problem into a weakly supervised pavement patch classification problem for solutions. Specifically, WSPLIN first divides the pavement image under different scales into patches with different collection strategies and then employs a Patch Label Inference Network (PLIN) to infer the labels of these patches to fully exploit the resolution and scale information. Notably, we design a patch label sparsity constraint based on the prior knowledge of distress distribution and leverage the Comprehensive Decision Network (CDN) to guide the training of PLIN in a weakly supervised way. Therefore, the patch labels produced by PLIN provide interpretable intermediate information, such as the rough location and the type of distress. We evaluate our method on a large-scale bituminous pavement distress dataset named CQU-BPDD and the augmented Crack500 (Crack500-PDD) dataset, which is a newly constructed pavement distress detection dataset augmented from the Crack500. Extensive results demonstrate the superiority of our method over baselines in both performance and efficiency. The source codes of WSPLIN are released on https://***/DearCaat/wsplin. © 2022, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Janus Msisnn4 (M= Mo;W)：High Efficiently Overall Water Splitting Photocatalyst Triggered By The Intrinsic Electric Field

SSRN

引用

SSRN 2023年

作者： Wang, Yi Wang, Yingchao Chen, Tengteng Li, Lei Wang, Guang Zhang, Zhengli Ding, Zhao Guo, Xiang Luo, Zijiang Liu, Xuefei College of Big Data and Information Engineering Guizhou University Guiyang550025 China Power Semiconductor Device Reliability Research Center Ministry of Education Guizhou University Guiyang550025 China Institute of Intelligent Manufacturing Shunde Polytechnic Guangdong Shunde528300 China Key Laboratory of Micro-Nano-Electronics of Guizhou Province Guiyang550025 China School of Physics and Electronic Science Guizhou Normal University Guiyang550025 China

Photocatalytic hydrolysis is one of the most effective ways for hydrogen fuel as a strategy for turning solar energy into hydrogen fuel. Two-dimensional(2D) Janus materials with an out-of-plane polarised electric field not only help to promote photogenerated carrier separation and migration but also lead to energy band bending, which enhances photo-oxidation and retains efficient absorption of visible light. In this manuscript, a systematic first-principles analysis was conducted on the WSn2N4 and MSiSnN4 (M= Mo;W) system. The results show that Janus MSiSnN4 (M= Mo;W) systems have a suitable bandgap and band edge location that include the redox position for water, together with abundant electron mobility(>200 cm2V-1s-1) and outstanding visible light optical absorption capacity(ηSTH = 23.12% for WSiSnN4;ηSTH = 32.91% for MoSiSnN4). The oxygen evolution reaction (OER) and hydrogen evolution reaction (HER) Gibbs free energy changes of WSiSnN4 show that it can make HER and OER processes occur spontaneously under light in acidic and neutral solutions, demonstrating excellent photocatalytic performance. © 2023, The Authors. All rights reserved.

关键词： Light absorption

来源：评论

学校读者我要写书评

暂无评论

Finding the most reliable maximum flow in transport network 2nd

Finding the most reliable maximum flow in transport network

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Wang, Jie Cai, Wei Zhou, Sihai Liu, Yundi Liao, Weicheng Zhang, Baili School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration of Ministry of Education Nanjing China Research Center for Judicial Big Data Supreme Count of China Nanjing211189 China

ISBN: (纸本)9789811561122

This paper intends to solve the most reliable maximum flow problem (MRMF) on transport network. A subgraph path division algorithm (SPDA) is proposed to get the most reliable maximum flow distribution, which avoid the negative impact of the number of simple paths and its bottleneck capacity. SPDA divides the sub-graph space of a transport network into a set of disjoint closed intervals, which satisfies the maximum flow constraints. Among the lower bounds of all the intervals, the one with discovered probability has proven to be the most reliable maximum. Finally, experimental results reveal the effectiveness and efficiency of the proposed algorithm. © Springer Nature Singapore Pte Ltd 2020.

关键词： Flow graphs

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：