检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Wu, Faming Hu, Yanxu Wang, Jinpeng Ma, Andy J. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Few-shot object detection is an important but challenging task where only a few instances of novel categories are available. The widely used approach is to pretrain a detector on base classes with abundant samples and then fine-tune it for novel classes. Due to the extreme data imbalance between base and novel classes, the detection performance of novel classes degrades with the distribution bias. To overcome this limitation, we propose a distribution calibration strategy and a class discrimination regularization method for better few-shot detection. Based on theoretical analysis on decision margins of base and novel classes, the decision area of novel classes is enlarged to balance the prediction probability. On the other hand, to increase the separability of inter-class distributions, the similarity between class-specific representations is minimized. Extensive experiments on PASCAL VOC and MS COCO datasets verify the effectiveness and generalization ability of our method to improve few-shot object detection. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised dictionary learning with label propagation for image classification

引用

Computational Visual Media 2017年第1期3卷 83-94页

作者： Lin Chen Meng Yang College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina School of Data and Computer Science Sun Yat-sen UniversityGuangzhouChina Key Laboratory of Machine Intelligence and Advanced Computing(Sun Yat-sen University) Ministry of EducationChina

Sparse coding and supervised dictionary learning have rapidly developed in recent years,and achieved impressive performance in image classification. However, there is usually a limited number of labeled training samples and a huge amount of unlabeled data in practical image classification,which degrades the discrimination of the learned dictionary. How to effectively utilize unlabeled training data and explore the information hidden in unlabeled data has drawn much attention of researchers. In this paper, we propose a novel discriminative semisupervised dictionary learning method using label propagation(SSD-LP). Specifically, we utilize a label propagation algorithm based on class-specific reconstruction errors to accurately estimate the identities of unlabeled training samples, and develop an algorithm for optimizing the discriminative dictionary and discriminative coding vectors *** experiments on face recognition, digit recognition, and texture classification demonstrate the effectiveness of the proposed method.

关键词： semi-supervised learning dictionary learning label propagation image classification

来源：评论

学校读者我要写书评

暂无评论

Region-Interactive Proposal Network and Class-Interactive Feature Learning for Few-Shot Object Detection

Region-Interactive Proposal Network and Class-Interactive Fe...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Hu, Yanxu Wu, Faming Wang, Jinpeng Ma, Andy J. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Few-shot object detection is a promising approach to solving the problem of detecting novel objects with only limited annotated data for training. Most existing methods are developed based on the progress in few-shot classification, which pay little attention to improving the localization module and modelling class interrelation. To address these issues, this paper proposes two novel modules, namely Region-interactive Proposal Network (Ri-PN) and Class-interactive Feature Learning (Ci-FL), for better localization and classification performance, respectively. In the Ri-PN, regions of novel classes are interacted with base classes via graph convolution instead of background due to the stronger relevance between base and novel classes together with the guidance of supervised regions loss. On the other hand, the Ci-FL refines class-specific features in prototypical learning by attentive graph convolutional network. Experimental results on PASCAL VOC and MS COCO datasets verify the superiority of our method for few-shot object detection. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap using Contrastive Learning and Semantic Consistency for Unsupervised Neural Machine Translation 5

Bridging the Gap using Contrastive Learning and Semantic Con...

引用

5th International Conference on Artificial intelligence and Computer engineering, ICAICE 2024

作者： Zhang, Chuancai Qu, Dan Du, Liming Yang, Kaiyuan School of Information Systems Engineering University of Information Engineering Zhengzhou China Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou China School of Cyberspace Security Zhengzhou University Zhengzhou China

ISBN: (纸本)9798331528911

In Unsupervised Neural Machine Translation (UNMT) tasks, the lack of extensive parallel corpora makes it challenging for the model to directly optimize the correspondence between the source and target languages. UNMT models primarily rely on learning from monolingual data, making it difficult to fully capture cross-linguistic semantic alignment and consistency during training. Therefore, effectively enhancing semantic alignment between the source and target languages under unsupervised conditions has become a key challenge in the field of UNMT. To address this issue, this study proposes a semantic alignment and consistency enhancement mechanism based on contrastive learning, aiming to improve the model's ability to capture cross-lingual semantic differences by constructing an optimization objective focused on semantic consistency. The method utilizes a pretrained cross-lingual model to generate semantic embeddings for both the source and target languages, then designs a contrastive learning-based loss function that minimizes the semantic distance between correct translations and source sentences while increasing the semantic distance between incorrect translations and source sentences, thereby enhancing the model's performance in semantic consistency. The experiments validate the effectiveness and broad applicability of the semantic consistency optimization method based on contrastive learning, demonstrating great potential and advantages, especially in multilingual tasks of UNMT. The model achieved significant improvements in BLEU scores across various language pairs. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAINTY ESTIMATION OF PSEUDO SUPERVISION

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAIN...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Chen, Xi Ma, Andy J. Guo, Nanxi Chen, Jiajia School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

Pseudo bounding box supervision is a promising approach for weakly supervised object localization (WSOL) with only image-level labels. However, the generated pseudo bounding boxes may be inaccurate or even completely non-overlapped with the objects of interest. In this paper, we propose to estimate the uncertainty of pseudo bounding boxes such that the negative impact caused by inaccurate estimation of pseudo supervision could be alleviated for better WSOL. The refined bounding boxes and corresponding variance uncertainties are learned by training a neural network regressor to penalize the erroneous estimations. To the best of our knowledge, this is the first work to incorporate uncertainty information of pseudo bounding boxes for WSOL. Experimental results show that our method not only outperforms previous state-of-the-art methods in CUB-200-2011 and ILSVRC datasets but also gives more precise bounding box prediction when the IoU threshold is higher. © 2021 IEEE

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

A New Noise-Tolerant Dual-Neural-Network Scheme for Robust Kinematic Control of Robotic Arms With Unknown Models

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1778-1791页

作者： Ning Tan Peng Yu Zhiyan Zhong Fenglei Ni IEEE the School of Computer Science and Engineering&Key Laboratory of Machine Intelligence and Advanced Computing Ministry of EducationSun Yat-sen UniversityGuangzhou 510006China the School of Automation Guangdong Polytechnic Normal UniversityGuangzhou 510665China the State Key Laboratory of Robotics and Systems Harbin Institute of Technology(HIT)Harbin 150080China

Taking advantage of their inherent dexterity,robotic arms are competent in completing many tasks *** a result of the modeling complexity and kinematic uncertainty of robotic arms,model-free control paradigm has been proposed and investigated ***,robust model-free control of robotic arms in the presence of noise interference remains a problem worth *** this paper,we first propose a new kind of zeroing neural network(ZNN),i.e.,integration-enhanced noise-tolerant ZNN(IENT-ZNN)with integration-enhanced noisetolerant ***,a unified dual IENT-ZNN scheme based on the proposed IENT-ZNN is presented for the kinematic control problem of both rigid-link and continuum robotic arms,which improves the performance of robotic arms with the disturbance of noise,without knowing the structural parameters of the robotic *** finite-time convergence and robustness of the proposed control scheme are proven by theoretical ***,simulation studies and experimental demonstrations verify that the proposed control scheme is feasible in the kinematic control of different robotic arms and can achieve better results in terms of accuracy and robustness.

关键词： Dual zeroing neural networks(ZNN) finite-time convergence model-free robot control robustness analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Sleep Staging Method Based on Multi-Scale Convolution and Self-Attention Mechanism 2

Research on Sleep Staging Method Based on Multi-Scale Convol...

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Pan, Dongdong Li, Yingying School of Computer and Artificial Intelligence Zhengzhou University China State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University China

ISBN: (纸本)9781510666733

Sleep is a very important physiological process for humans, and sleep staging is an important basis for evaluating sleep quality and diagnosing sleep-related diseases. Manual sleep staging is time-consuming and laborious, and the staging results are easily affected by subjective factors. Therefore, the research on automatic sleep staging models has extremely high research value and clinical application value. This paper proposes a sleep staging method based on multi-scale one-dimensional convolutional neural network and self-attention mechanism. The attention mechanism mines the channel correlation and temporal correlation of different channels respectively. This paper selects the sleep data of 153 normal subjects in the public dataset Sleep-EDF for model training and testing. The average staging accuracy rate was 84.5%, and the consistency test value was 0.781, which was better than the consistency test value of 0.75 for the inter-physician score. The experimental results show that the algorithm model in this paper has a high staging effect, can make full use of sleep data, and has important research significance for assisting clinicians in rapid sleep staging. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Survey on the Improvement and Application of HHL Algorithm

Survey on the Improvement and Application of HHL Algorithm

引用

2022 International Conference on Computer Modelling and Big Data Analytics, CMBDA 2022

作者： Liu, Xiaonan Xie, Haoshan Liu, Zhengyu Zhao, Chenyan State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University ZhengZhou450000 China School of Computer and Artificial Intelligence ZhengZhou University ZhengZhou450000 China

Quantum computing is a new computing mode that follows the laws of quantum mechanics to control quantum information units for computation. In terms of computational efficiency, due to the existence of quantum mechanical superposition, some known quantum algorithms can process problems faster than traditional general-purpose computers. HHL algorithm is an algorithm for solving linear system problems. Compared with classical algorithms in solving linear equations, it has an exponential acceleration effect in certain cases and as a sub-module, it is widely used in some machine learning algorithms to form quantum machines learning algorithms. However, there are some limiting factors in the use of this algorithm, which affect the overall effect of the algorithm. How to improve it to make the algorithm perform better has become an important issue in the field of quantum computing. This paper summarizes the optimization and improvement of HHL algorithm since it was proposed, and the application of HHL algorithm in machine learning, and discusses some possible future improvements of some subroutines in HHL algorithm. © Published under licence by IOP Publishing Ltd.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Inequality-Type Zhang Equivalency of Great-Than-or-Equal-to (GTOET) Sign in Matrix-Vector,Matrix,and Integral Situations Applied to Obstacle Avoidance 41

Inequality-Type Zhang Equivalency of Great-Than-or-Equal-to ...

引用

第41届中国控制会议

作者： Yunong Zhang Jianzhen Xiao School of Computer Science and Engineering Sun Yat-sen University Research Institute of Sun Yat-sen University in Shenzhen Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,the concept of Zhang equivalency(ZE) and equality-type ZE are *** the basis of equalitytype ZE,we introduce the inequality-type ZE of great-than-or-equal-to(GTOET) sign and thus propose the order-1,order-2,and order-3 general formulas of the inequality-type ZE of GTOET ***,we investigate the inequality-type ZE of GTOET sign in three different and appealing situations,including matrix-vector situation,matrix situation,and integral ***,the corresponding formulas are *** distance between a certain object and an obstacle can be considered as the point-to-point distance,and thus the obstacle avoidance scheme is described as an *** by that thought,we apply the inequality-type ZE of GTOET sign to the matrix-form obstacle avoidance.

关键词： Zhang equivalency Great-than-or-equal-to(GTOET) sign Inequalities Obstacle avoidance

来源：评论

学校读者我要写书评

暂无评论

Software Diversification Protection Methods for Binary Programs

Software Diversification Protection Methods for Binary Progr...

引用

6th International Conference on Intelligent computing and Signal Processing (ICSP)

作者： Yingchao Chen Junchao Wang Xin Zhou Jianmin Pang Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Software diversification is an effective software protection method against reverse engineering and code reuse attacks, which can provide heterogeneous redundant execution bodies for mimetic defense mechanisms. Most existing software diversification methods require access to the source code, which can provide defenders with more valuable information for devising effective defense strategies. However, due to commercial copyright and the purpose of preventing software piracy, developers often keep their software closed-source, making it difficult to access the source code. Therefore, a method called R2BF (ReCooking and Randomizing Binary File) is proposed, which combines decompilation and diversification compilation techniques to address the difficulty of obtaining the source code. This method involves diversifying the source code through compilation to achieve software diversification for binary executable files. Security and performance testing of diversified C programs has shown that diversified binary executable files can mitigate vulnerabilities resulting from code reuse, validating that this method can enhance the security of binary programs and is feasible for software protection. The diversified binary executable files are nearly identical to the original, non-diversified files in terms of file size and execution time, and may even exhibit acceleration and optimization effects in certain scenarios.

关键词： Software testing Codes Source coding Software protection Software algorithms Reverse engineering Signal processing algorithms Software Security Optimization

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：