检索结果-内蒙古大学图书馆

16th International Conference on Digital Image Processing, ICDIP 2024

作者： Zhang, Qian Ran, Yaqin Luo, Di Xu, Kaili Shi, Jilaing School of Data Science and Information Engineering GuiZhou MinZu University Guiyang550025 China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guiyang550025 China

ISBN: (数字)9781510682917

ISBN: (纸本)9781510682900

It's very meaningful to conduct the driver to the parking space available in the parking lot clearly and accurately by computer vision and computational intelligence. While it is an extremely difficult task, because of the scene complexity in the parking lot. In this paper, a new computational intelligence technology is proposed to detect parking spaces available in the parking lot outdoor based on fusing of Region Convolution Neural Network (RCNN) and random forests (RF), and we called it as RCNN-RF. Within the RCNN-RF, a new activation function is design. And with the help of random forests, RCNN-RF overcomes scene complexity includes illumination, weather, and slight occlusion successfully. Extensive experimental results on the benchmark dataset named PKLot and the self-built dataset named GZMU-LOT outperform those of the state-of-the-art, and it shows the superiority of our proposed RCNN-RF method. © 2024 SPIE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration

Learning Discriminative Representations for Open Relation Ex...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Wang, Shusen Duan, Bin Wu, Yanan Xu, Yajing Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781955917766

Open relation extraction is the task to extract relational facts without pre-defined relation types from open-domain corpora. However, since there are some hard or semi-hard instances sharing similar context and entity information but belonging to different underlying relation, current OpenRE methods always cluster them into the same relation type. In this paper, we propose a novel method based on Instance Ranking and Label Calibration strategies (IRLC) to learn discriminative representations for open relation extraction. Due to lacking the original instance label, we provide three surrogate strategies to generate the positive, hard negative, and semi-hard negative instances for the original instance. Instance ranking aims to refine the relational feature space by pushing the hard and semi-hard negative instances apart from the original instance with different margins and pulling the original instance and its positive instance together. To refine the cluster probability distributions of these instances, we introduce a label calibration strategy to model the constraint relationship between instances. Experimental results on two public datasets demonstrate that our proposed method can significantly outperform the previous state-of-the-art methods. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction

RCL: Relation Contrastive Learning for Zero-Shot Relation Ex...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Wang, Shusen Zhang, Bosen Xu, Yajing Wu, Yanan Xiao, Bo Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781955917766

Zero-shot relation extraction aims to identify novel relations which cannot be observed at the training stage. However, it still faces some challenges since the unseen relations of instances are similar or the input sentences have similar entities, the unseen relation representations from different categories tend to overlap and lead to errors. In this paper, we propose a novel Relation Contrastive Learning framework (RCL) to mitigate above two types of similar problems: Similar Relations and Similar Entities. By jointly optimizing a contrastive instance loss with a relation classification loss on seen relations, RCL can learn subtle difference between instances and achieve better separation between different relation categories in the representation space simultaneously. Especially in contrastive instance learning, the dropout noise as data augmentation is adopted to amplify the semantic difference between similar instances without breaking relation representation, so as to promote model to learn more effective representations. Experiments conducted on two well-known datasets show that RCL can significantly outperform previous state-of-the-art methods. Moreover, if the seen relations are insufficient, RCL can also obtain comparable results with the model trained on the full training set, showing the robustness of our approach. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cluster-aware Pseudo-Labeling for Supervised Open Relation Extraction 29

Cluster-aware Pseudo-Labeling for Supervised Open Relation E...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Duan, Bin Wang, Shusen Liu, Xingxian Xu, Yajing Pattern Recognition & Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Supervised open relation extraction aims to discover novel relations by leveraging supervised data of pre-defined relations. However, most existing methods do not achieve effective knowledge transfer from pre-defined relations to novel relations, they have difficulties generating high-quality pseudo-labels for unsupervised data of novel relations and usually suffer from the error propagation issue. In this paper, we propose a Cluster-aware Pseudo-Labeling (CaPL) method to improve the pseudo-labels quality and transfer more knowledge for discovering novel relations. Specifically, the model is first pre-trained with the pre-defined relations to learn the relation representations. To improve the pseudo-labels quality, the distances between each instance and all cluster centers are used to generate cluster-aware soft pseudo-labels for novel relations. To mitigate the catastrophic forgetting issue, we design the consistency regularization loss to make better use of the pseudo-labels and jointly train the model with both unsupervised and supervised data. Experimental results on two public datasets demonstrate that our proposed method achieves new state-of-the-arts performance © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Size and Defect Detection of Valve Based on Computer Vision

Size and Defect Detection of Valve Based on Computer Vision

引用

2022 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2022

作者： Yan, Xiaobo Feng, Le Tan, Mian Yang, Yuan Zhang, Yu Wang, Lin Guizhou Key Laboratory of Pattern Recognition and Intelligent System China Guizhou Minzu University Guiyang550025 China Guiyang Fusheng Intelligent Technology Co. Ltd China

ISBN: (纸本)9781510663350

Engine valve is the core component of the engine, and its quality determines the performance of the engine. In industrial production quality inspection, it is necessary to detect the size of the valve and whether there are defects on the surface. Usually, the quality of the valve is determined by comparing the image of the valve surface with the standard image. However, the existing surface defect detection technology cannot detect the curved surface device. In order to solve this problem, this paper designs a valve size and defect detection method based on computer vision. The experimental results show that the method can quickly and accurately detect the rod diameter, groove radius and surface defects of the valve. The method is practical, robust and real-time. © 2023 SPIE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

intelligent Parking Big Data Cloud Platform Algorithm Research and Application 6

Intelligent Parking Big Data Cloud Platform Algorithm Resear...

引用

6th International Conference on Computer Information Science and Application Technology, CISAT 2023

作者： Yan, Xiaobo Zou, Xue Cai, Shan Wang, Lin Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province Guizhou Minzu University Guiyang China College of Date Science and Information Engineering Guizhou Minzu University Guiyang China

ISBN: (纸本)9781510668546

With the rapid development of the domestic economy and the increasing living standards of the people, the ownership of private cars has increased explosively. Currently, urban traffic congestion and parking difficulty have gradually become a hot topic of research from all walks of life. Parking difficulty is mainly reflected on the following aspects: first, the existing parking spaces in cities are not effectively utilized;The second reason is that drivers cannot grasp relevant information about parking spaces near the ground in real time. This article conducts in-depth research on the issue of parking difficulty. Based on the existing security monitoring systems in parking lots, real-time detection of parking spaces status is conducted based on computer vision, machine learning, and other methods. By building a comprehensive, synthesize, and multi-dimensional parking resources dynamic sensing system, a smart parking big data cloud platform is constructed to achieve the effect of intelligent indoor parking lots management. © 2023 SPIE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Structural Connectivity Enhanced Anisotropic 3D Network for Brain Midline Delineation

引用

Journal of Beijing Institute of Technology 2023年第5期32卷 562-578页

作者： Yufan Liu Kongming Liang Yinuo Jing Shen Wang Zhanyu Ma Yiming Li Yizhou Yu Yizhou Wang Jun Guo Pattern Recognition and Intelligent System Laboratory School of Artificial IntelligenceBeijing University of Posts and TelecommunicationsBeijing 100876China. Center on Frontiers of Computing Studies School of Computer SciencePeking UniversityBeijing 100871China AI Lab Deepwise HealthcareBeijing 100089China

Brain midline delineation can facilitate the clinical evaluation of brain midline shift,which has a pivotal role in the diagnosis and prognosis of various brain ***,there are still challenges for brain midline delineation:1)the largely deformed midline is hard to localize if mixed with severe cerebral hemorrhage;2)the predicted midlines of recent methods are not smooth and continuous which violates the structural *** overcome these challenges,we propose an anisotropic three dimensional(3D)network with context-aware refinement(A3D-CAR)for brain midline *** proposed network fuses 3D context from different two dimensional(2D)slices through asymmetric context *** exploit the elongated structure of the midline,an anisotropic block is designed to balance the difference between the adjacent pixels in the horizontal and vertical *** maintaining the structural priority of a brain midline,we present a novel 3D connectivity regular loss(3D CRL)to penalize the disconnectivity between nearby *** experiments on the CQ dataset and one in-house dataset show that the proposed method outperforms three state-of-the-art methods on four evaluation metrics without excessive computational burden.

关键词： brain midline delineation refinement network structure prior connectivity regular loss

来源：评论

学校读者我要写书评

暂无评论

Feature Decoupled of Deep Mutual Information Maximization 2

Feature Decoupled of Deep Mutual Information Maximization

引用

2nd International Conference on Automation, Robotics and Computer Engineering, ICARCE 2023

作者： He, Xing Peng, Changgen Wang, Lin Tan, Weijie Wang, Zifan State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China Guizhou Big Data Academy Guizhou University Guiyang China Guizhou Minzu University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guiyang China Institute of Guizhou Aerospace Measuring and Testing Technology Guiyang China

ISBN: (纸本)9798350308341

In deep learning, supervised learning techniques usually require a large amount of expensive labeled data to train the network, and the feature representations extracted by the model usually mix multiple attributes, resulting in feature representations that are difficult to decouple and are non-interpretable, which restricts the application and development of deep learning techniques, and for this reason, it is particularly important to study decoupled feature representation methods for unsupervised learning. Although the Learning deep representations by mutual information estimation and maximization (DIM) method achieves excellent results in unsupervised learning, the feature representations learned by the DIM method still suffer from the problem of difficult decoupling. decoupling problem. To address this problem, we minimize the mutual information between the intermediate layer feature representations learned by the hidden layer of the encoder during the encoder training process, so that the features learned by each filter are as uncorrelated as possible, thus realizing feature decoupling, and our method is called FP-DIM. Finally, the effectiveness of the FP-DIM method is verified on the CIFAR-10, STL-10, and Fashion-MNIST datasets. The experiments show that our proposed FP-DIM method is more significant for the learned decouplable middle layer feature representation. Finally, we also propose a reflection of future research for the FP-DIM method, aiming to provide a research idea and direction for solving unsupervised interpretable machine learning and to lay a solid theoretical and application foundation for machine learning fields such as image classification and migration learning. © 2023 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Interpretable Defense Against Adversarial Attacks via Causal Inference

引用

Machine Intelligence Research 2022年第3期19卷 209-226页

作者： Min Ren Yun-Long Wang Zhao-Feng He University of Chinese Academy of Sciences Beijing 100190China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China Laboratory of Visual Computing and Intelligent System Beijing University of Posts and TelecommunicationsBeijing 100876China

Deep learning-based models are vulnerable to adversarial attacks. Defense against adversarial attacks is essential for sensitive and safety-critical scenarios. However, deep learning methods still lack effective and efficient defense mechanisms against adversarial attacks. Most of the existing methods are just stopgaps for specific adversarial samples. The main obstacle is that how adversarial samples fool the deep learning models is still unclear. The underlying working mechanism of adversarial samples has not been well explored, and it is the bottleneck of adversarial attack defense. In this paper, we build a causal model to interpret the generation and performance of adversarial samples. The self-attention/transformer is adopted as a powerful tool in this causal model. Compared to existing methods, causality enables us to analyze adversarial samples more naturally and intrinsically. Based on this causal model, the working mechanism of adversarial samples is revealed, and instructive analysis is provided. Then, we propose simple and effective adversarial sample detection and recognition methods according to the revealed working mechanism. The causal insights enable us to detect and recognize adversarial samples without any extra model or training. Extensive experiments are conducted to demonstrate the effectiveness of the proposed methods. Our methods outperform the state-of-the-art defense methods under various adversarial attacks.

关键词： Adversarial sample adversarial defense causal inference interpretable machine learning transformers

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition under occlusion conditions based on multi-feature cross-attention

引用

Journal of intelligent and Fuzzy systems 2024年第4期46卷 9841-9856页

作者： Guo, Sheng Tan, Mian Cai, Shan Zhang, Zaijun Liang, Yihui Feng, Hongxi Zou, Xue Wang, Lin School of Data Science and Information Engineering Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China School of Mathematics and Statistics Qiannan Normal University for Nationalities Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Duyun China Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Aerospace Tianma Electromechanical Technology Co LTD Zunyi China

Although facial expression recognition (FER) has a wide range of applications, it may be difficult to achieve under local occlusion conditions which may result in the loss of valuable expression features. This issue has motivated the present study, as a part of which an effective multi-feature cross-attention network (MFCA-Net) is proposed. The MFCA-Net consists of a two-branch network comprising a multi-feature convolution module and a local cross-attention module. Thus, it enables decomposition of facial features into multiple sub-features by the multi-feature convolution module to reduce the impact of local occlusion on facial expression feature extraction. In the next step, the local cross-attention module distinguishes between occluded and unoccluded sub-features and focuses on the latter to facilitate FER. When the MFCA-Net performance is evaluated by applying it to three public large-scale datasets (RAF-DB, FERPlus, and AffectNet), the experimental results confirm its good robustness. Further validation is performed on a real FER dataset with local occlusion of the face. © 2024 – IOS Press.

关键词： Convolution

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：