检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Zhang, Siqing Du, Ruoyi Chang, Dongliang Ma, Zhanyu Guo, Jun The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665438643

Fine-grained visual classification (FGVC) aims to distinguish the sub-classes of the same category and its essential solution is to mine the subtle and discriminative regions. Convolution neural networks (CNNs), which employ the cross entropy loss (CE-loss) as the loss function, show poor performance since the model can only learn the most discriminative part and ignore other meaningful regions. Some existing works try to solve this problem by mining more discriminative regions by some detection techniques or attention mechanisms. However, most of them will meet the background noise problem when trying to find more discriminative regions. In this paper, we address it in a knowledge transfer learning manner. Multiple models are trained one by one, and all previously trained models are regarded as teacher models to supervise the training of the current one. Specifically, a orthogonal loss (OR-loss) is proposed to encourage the network to find diverse and meaningful regions. In addition, the first model is trained with only CE-Loss. Finally, all models' outputs with complementary knowledge are combined together for the final prediction result. We demonstrate the superiority of the proposed method and obtain state-of-the-art (SOTA) performances on three popular FGVC datasets. © 2021 IEEE

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Clarity in chaos: Boosting few-shot classification through information suppression and sparsification

引用

pattern recognition 2025年 167卷

作者： Li, Xiaoxu Ji, Luchen Zhu, Rui Ma, Zhanyu Xue, Jing-Hao School of Computer and Communication Lanzhou University of Technology Lanzhou730050 China Faculty of Actuarial Science and Insurance Bayes Business School City St George's University of London LondonEC1Y 8TZ United Kingdom Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Department of Statistical Science University College London LondonWC1E 6BT United Kingdom

The advance of deep learning has invigorated the research of few-shot classification. However, the interference of non-target information in feature representations hampers classification generalization. To tackle this issue, we propose an irrelevant information suppression (IIS) module, which is focused on suppressing the weight of unimportant information and elevating the sparsity of feature representations. An IIS network with three consecutive IIS modules is developed, to illustrate the progressive suppression of unimportant information and highlighting of key discriminative features of the target. Extensive experiments showcase the superior performance of our IIS network on five widely-used benchmark datasets. Furthermore, we show that the IIS module can be readily used as a plug-in module by state-of-the-art few-shot classifiers, and can clearly further improve their performance. Our code is available on GitHub at https://***/LC4188/IISNet. © 2025

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Tracking system for driving assistance with the faster R-CNN 2nd

Tracking system for driving assistance with the faster R-CNN

引用

2nd International Conference on Computer, Communication and Computational Sciences, IC4S 2017

作者： Yang, Kai Zhang, Chuang Wu, Ming Pattern Recognition and Intelligent System Lab School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9789811303432

The vehicle detection and tracking in driving assistance system are ordinarily achieved by the optical or radar technology. In this work, we explore video processing for driving assistance system. An object’s detection and tracking system based on the Faster R-CNN and Camshift algorithm is proposed, and Kalman filtering algorithm is used to predict the position of objects. Our system differs with other object-tracking algorithms based on deep learning, which directly detects each frame and has no tracking part, such as YOLO and SSD. We also introduce an evaluation criterion for driving assistance system according to the dangerous level of the surrounding cars. Through the experiments on the videos recorded by drive recorder, we show that our approach can achieve better performance in complex scenes than YOLO or SSD and can satisfy the real-time requirement by processing 30 frames per second. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CROSS-MODAL SUBSPACE LEARNING FOR SKETCH-BASED IMAGE RETRIEVAL:A COMPARATIVE STUDY 5

CROSS-MODAL SUBSPACE LEARNING FOR SKETCH-BASED IMAGE RETRIEV...

引用

2016 5th IEEE International Conference on Network Infrastructure and Digital Content(IC-NIDC 2016)

作者： Peng Xu Ke Li Zhanyu Ma Yi-Zhe Song Liang Wang Jun Guo Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications SketchX Lab School of Electronic Engineering and Computer ScienceQueen Mary University of London National Lab of Pattern Recognition Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781509012473

Sketch-based image retrieval（SBIR）has become a prominent research topic in recent years due to the proliferation of touch *** problem is however very challenging for that photos and sketches are inherently modeled in different *** are accurate（colored and textured）depictions of the real-world,whereas sketches are highly abstract（black and white）renderings often drawn from human *** naturally motivates us to study the effectiveness of various cross-modal retrieval methods in ***,to the best of our knowledge,all established cross-modal algorithms are designed to traverse the more conventional cross-modal gap of image and text,making their general applicableness to SBIR *** this paper,we design a series of experiments to clearly illustrate circumstances under which cross-modal methods can be best utilized to solve the SBIR *** specifically,we choose six state-of-the-art cross-modal subspace learning approaches that were shown to work well on image-text and conduct extensive experiments on a recently released SBIR ***,we present detailed comparative analysis of the experimental results and offer insights to benefit future research.

关键词： SBIR Cross-modal Subspace learning Comparison

来源：评论

学校读者我要写书评

暂无评论

Matching image with multiple local features

Matching image with multiple local features

引用

International Conference on pattern recognition

作者： Cao, Yudong Zhang, Honggang Gao, Yanyan Xu, Xiaojun Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Liaoning University of Technology Jinzhou China

ISBN: (纸本)9780769541099

In this paper, we present the fusional feature composed of Affine-SIFT, MSER and color moment invariants. The fusional feature is more robust and distinctive than a single local feature. Instead of adding three local features together simply, an efficient two-level matching strategy is devised with the fusional feature, which speeds up the establishment of the local correspondences. To remove partial false positives, an affine transformation is estimated with the weighted RANSAC which decreases iteration times. The experimental results show that our approach can achieve more accurate correspondence. We prospect to apply the fusional feature and match strategy to image retrieval in the end. © 2010 IEEE.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Resume parser: Semi-structured Chinese document anlysis

Resume parser: Semi-structured Chinese document anlysis

引用

2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009

作者： Zhang, Chuang Wu, Ming Li, Chun Guang Xiao, Bo Lin, Zhi-Qing Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications Mailbox186 Beijing 100876 China

ISBN: (纸本)9780769535074

Semi-structured Chinese document anlysis is the most diffcult task for complex structure and Chinese semantics. According to the generic characteristics of the semi-structured document and the specific characteristics of the resume document, the paper researched on resume document block anlysis based on pattern matching, multi-level information identification and feedback control algorithms was also prompted. Based on the research, Resume Parser system was implemented for ChinaHR, which is the biggest recruitment website. It can read, analysis, retrieval and store the information automatically. According to all kinds of experienments results, the accuracy and efficiency of this system can generally satisfy the practical requirements. As the research on the processing of the semi-structured document, it will not only be as a directive of the further research on the resume analysis, but also be as the reference to other form of the semi-structured document. © 2008 IEEE.

关键词： pattern matching

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

The architecture of centralized access control proxy server based on NETCONF

The architecture of centralized access control proxy server ...

引用

International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2010

作者： Wang, Feng Zhang, Bin Li, Guohui Guo, Jun Li, Yan Gao, Xuesong Pattern Recognition and Intelligent System Lab. Beijing University of Post and Telecommunications Beijing China HuaWei Beijing Research Institute Beijing China

ISBN: (纸本)9780769539621

NETCONF is a new protocol as the network becomes more and more complexity, which has a better capability administering lots of devices. However, the large scale network brings some trouble for implementing access control especially when administers need to deploy or update policies on each devices. In this regard, the architecture of centralized access control proxy server based on NETCONF is focused, which realizes policies management and authorization centralized and raises administration efficiency. In order to figure it out absolutely, we present the basic theory giving the detailed illustration about components of the architecture. Finally, we describe how dose the architecture work based on NETCONF. © 2010 IEEE.

关键词： Network architecture

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

Unsupervised Learning of Gaussian Mixture Model with Application to Image Segmentation

引用

电子学报(英文版) 2010年第3期19卷 451-456页

作者： LI Bo LIU Wenju DOU Lihua School of Automation Beijing Institute of Technology Beijing China Key Laboratory of Complex System Intelligent Control and Decision (Beijing Institute of Technology) Ministry of Education Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

Density estimation via Gaussian mixture modeling has been successfully applied to image segmentation, speech processing and other fields relevant to clustering analysis and Probability density function (PDF) modeling. Finite Gaussian mixture model is usually used in practice and the selection of number of mixture components is a significant problem in its application. For example, in image segmentation, it is the donation of the number of segmentation regions. The determination of the optimal model order therefore is a problem that achieves widely attention. This paper proposes a degenerating model algorithm that could simultaneously select the optimal number of mixture components and estimate the parameters for Gaussian mixture model. Unlike traditional model order selection method, it does not need to select the optimal number of components from a set of candidate models. Based on the investigation on the property of the elliptically contoured distributions of generalized multivariate analysis, it select the correct model order in a different way that needs less operation times and less sensitive to the initial value of EM. The experimental results show the effectiveness of the algorithm.

关键词：高斯混合模型图像分割无监督学习应用概率密度函数椭球等高分布模型估计高斯密度

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：