检索结果-内蒙古大学图书馆

Unlearning Recently Learned Data to Preserve Historical Learning for Dynamic Data Stream Classification

Chinese Journal of Electronics 2025年第3期34卷 849-860页

作者： Wen Yimin Zhou Xingzhi Liu Xiang Xue Yun Bin Chenzhong Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin 541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin 541004 China School of Municipal and Surveying Engineering Hunan City University Yiyang 413000 China

At present, dynamic data stream classification has achieved many successful results through concept drift detection and ensemble learning. However, generally, due to delay in concept drift detection, the active classifier may further learn data belonging to a new concept. This will ultimately degrade the generalization capability of this active classifier on its corresponding concept. Thus, how can a classifier corresponding to one concept unlearns the learned data belonging to another concept? Two unlearning algorithms are proposed to address this problem. The first one based on the passive-aggressive (PA) algorithm adopts the least squares method to reversely update the already-trained model, achieving the effect of approximately unlearning, while another based on a modified PA algorithm achieves complete unlearning by modifying the loss function of the PA algorithm. The comprehensive experiments illustrated the effectiveness of these proposed methods.

关键词： Data stream Machine unlearning Concept drift Online learning

来源：评论

学校读者我要写书评

暂无评论

PCRTAM-Net:A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation

引用

Journal of Computer Science & Technology 2023年第3期38卷 567-581页

作者：汪华登李紫正保罗黎兵兵潘细朋刘振丙蓝如师罗笑南 Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin 541004China School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin 541004China School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China Department of Pathology Ganzhou Municipal HospitalGanzhou 341000China

Retinal images play an essential role in the early diagnosis of ophthalmic *** segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the retinal vessels and the low-contrast *** the same time,automated models struggle to capture representative and discriminative retinal vascular *** fully utilize the structural information of the retinal blood vessels,we propose a novel deep learning network called Pre-Activated Convolution Residual and Triple Attention Mechanism Network(PCRTAM-Net).PCRTAM-Net uses the pre-activated dropout convolution residual method to improve the feature learning ability of the *** addition,the residual atrous convolution spatial pyramid is integrated into both ends of the network encoder to extract multiscale information and improve blood vessel information flow.A triple attention mechanism is proposed to extract the structural information between vessel contexts and to learn long-range feature *** evaluate the proposed PCRTAM-Net on four publicly available datasets,DRIVE,CHASE_DB1,STARE,and *** model achieves state-of-the-art performance of 97.10%,97.70%,97.68%,and 97.14%for ACC and 83.05%,82.26%,84.64%,and 81.16%for F1,respectively.

关键词： retinal image segmentation triple attention mechanism atrous convolution residual network

来源：评论

学校读者我要写书评

暂无评论

A cross-domain person re-identification algorithm based on distribution-consistency and multi-label collaborative learning

引用

Multimedia Tools and Applications 2024年第38期83卷 85939-85962页

作者： Zhang, Baohua Hao, Chen Lv, Xiaoqi Gu, Yu Wang, Yueming Liu, Xin Ren, Yan Li, Jianjun School of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou014010 China School of Information Engineering Mongolia Industrial University Inner Mongolia Huhehaote010051 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Inner Mongolia Baotou014010 China

To decrease domain shift in cross-domain person re-identification, existing methods generate pseudo labels for training models, however, the inherent distribution between source domain data and the hard quantization loss is ignored. Therefore, a cross-domain person re-identification method based on distribution consistency and multi-label collaborative learning is proposed. Firstly, a soft binary cross-entropy loss function is constructed to constrain the inter-sample relationship of cross-domain transformation, which can ensure the consistency of appearance features and sample distribution, and achieving feature cross-domain alignment. On this basis, in order to suppress the noise of hard pseudo labels, a multi-label collaborative learning network is constructed. The soft pseudo labels are generated by using the collaborative foreground features and global features to guide the network training, making the model adapt to the target domain. The experimental results show that the proposed method has better performance than that of recent representative methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Zhuang Characteristic Culture Detection Based on Improved YOLOV3-SPP Network 14th

Zhuang Characteristic Culture Detection Based on Improved YO...

引用

14th International Conference on Genetic and Evolutionary Computing, ICGEC 2021

作者： Guo, Shu Qiang, Baohua Xie, Wu Zhai, Yijie Chen, Ruidong Zheng, Hong Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9789811684296

In order to enhance the dissemination power of Zhuang culture and enhance the influence of traditional Chinese culture, this article proposes a data set containing the characteristic cultural products of the Zhuang nationality for the unique cultural development of the Zhuang nationality. The data set has a total of 1890 images and contains three categories, namely Zhuang Five-color glutinous rice, Zhuang Bronze drum, and Zhuang Hydrangea. At the same time, the YOLOV3-SPP network based on the darknet53 model is improved, and the ResNet101 structure is introduced to improve the robustness of the network. The verification results on the Zhuang characteristic data set show that the improved YOLOV3-SPP network has an accuracy rate of 92.78% on the Zhuang characteristic data set, which is 1.28% higher than the original YOLOV3-SPP network. The experimental results show that the improved YOLOV3-SPP structure can better realize the detection of the characteristic culture of the Zhuang nationality. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： YOLOV3-SPP model Zhuang characteristic data set Zhuang culture

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition In-the-Wild with Deep Pre-trained Models 17th

Facial Expression Recognition In-the-Wild with Deep Pre-tra...

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Li, Siyang Xu, Yifan Wu, Huanyu Wu, Dongrui Yin, Yingjie Cao, Jiajiong Ding, Jingting Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Ant Group Hangzhou China

ISBN: (纸本)9783031250743

Facial expression recognition (FER) is challenging, when transiting from the laboratory to in-the-wild situations. In this paper, we present a general framework for the Learning from Synthetic Data Challenge in the 4th Affective Behavior analysis In-The-Wild (ABAW4) competition, to learn as much knowledge as possible from synthetic faces with expressions. To cope with four problems in training robust deep FER models, including uncertain labels, class imbalance, mismatch between pretraining and downstream tasks, and incapability of a single model structure, our framework consists of four respective modules, which can be utilized for FER in-the-wild. Experimental results on the official validation set from the competition demonstrated that our proposed approach outperformed the baseline by a large margin. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

keycap character detection model based on target classification 7

Keycap character detection model based on target classificat...

引用

2024 7th International Conference on intelligent Manufacturing and Automation, IMA 2024

作者： Xiong, Taiping Zhu, Zhiguo Wang, Tinghao School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Key Laboratory of Image Graphics and Intelligent Processing in Guangxi Guilin University of Electronic Technology Guangxi Guilin541004 China

The production process of keycaps may result in surface character defects. The existing keycap character defect detection technology has low efficiency and accuracy, hindering the automation of keycap manufacturing. Addressing the challenge of extracting the entire keyboard from illuminated regions, this paper proposes a method using image feature points for template matching to extract the region of interest. Subsequently, leveraging prior knowledge, the paper addresses character segmentation and extraction on the keyboard. For character detection, the paper preprocesses images and classifies them by using an S-VGG network, yielding corresponding labels. © Published under licence by IOP Publishing Ltd.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Integrating the dynamic optimization strategies of Adam and AdaGrad

Integrating the dynamic optimization strategies of Adam and ...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Zhixuan Huang Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Artificial intelligence (AI) has been a key research area since the 1950s, initially focused on using logic and reasoning to create systems that understand language, control robots, and offer expert advice. With the rise of big data and deep learning, AI has advanced in applications like recommendation systems, image recognition, and machine translation, primarily through optimizing loss functions in deep neural networks to improve accuracy and reduce training *** descent is the core optimization method but faces challenges like slow convergence and local minima. To overcome these, algorithms like Momentum, AdaGrad, RMSProp, Adadelta, Adam, and Nadam have been developed, introducing momentum and adaptive learning rates to accelerate convergence. This paper presents a new optimization algorithm that combines the strengths of Adam and AdaGrad, offering better adaptability to different learning rates.

关键词： Training Heuristic algorithms Optimization methods Machine translation Logic Artificial intelligence Robots Recommender systems Convergence intelligent control

来源：评论

学校读者我要写书评

暂无评论

Attitude Detection Model Based on Improved High Resolution Network

Attitude Detection Model Based on Improved High Resolution N...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Dongliang Shi Yuhan Li Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

2D human posture detection, a challenging task in computer vision, aims to identify human body key points and is widely used. The HRNet model performs well in human key point detection. To enhance its effect in human posture detection and address suboptimal prediction accuracy in interactive occlusion, this paper combines HRNet and Transformer. The Transformer's attention mechanism handles complex image dependencies, and HRNet obtains image features. By embedding the Transformer's attention mechanism module into HRNet's backbone network and integrating a self-designed double-branch structure and convolutional attention module an improved HRNet model is constructed. The DConvAttention module processes extracted features and the convolutional attention mechanism balances image frequencies, enhancing processing and discrimination of complex backgrounds and occlusions and improving detection performance. In tests of complex and occluded images, the improved HRNet Local model has a 4.2M parameter increase, 0.5G FLOPs increase, and 1% mAP increase compared to HRNet, with the same recall rate. The improved HRNet Global model has 11M more parameters, 1.1G more FLOPS a similar or slightly higher recall rate, and a 2% higher mAP value.

关键词： Computer vision Attention mechanisms Accuracy Attitude control Computational modeling Information processing Transformers Feature extraction intelligent control

来源：评论

学校读者我要写书评

暂无评论

Improved LYT-Net image Enhancement Model for Underwater Robotics Vision

Improved LYT-Net Image Enhancement Model for Underwater Robo...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Wenjie Li Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Although underwater robots can replace humans to explore the ocean which is rich in resources but fraught with unknown risks, there are phenomena such as monotonous colors, complex backgrounds and uneven illumination in the underwater environment, which makes it difficult for underwater robots relying on the optical vision system to obtain clear images and is not conducive to subsequent recognition and grasping tasks. In this paper, relevant preparatory work was carried out for underwater image processing applicable to underwater robots, and the underwater imaging model as well as other underwater image processing models were analyzed. Subsequently, a method combining the underwater physical model and the dark channel image was proposed to improve LYT-Net, enabling it to be applicable to mobile embedded devices such as underwater robots. After training and testing on the real datasets LSUI and UIEB, our model achieved good results on important indicators such as PSNR and SSIM. Meanwhile, it met the theoretical requirements of mobile devices in terms of FLOPs, Params and single-frame processing time, which verified its robustness and real-time processing ability in various underwater environments.

关键词： Training Autonomous underwater vehicles Analytical models Visualization image recognition image color analysis Stability analysis Robots image enhancement Testing

来源：评论

学校读者我要写书评

暂无评论

Fog images Generation About Unmanned Surface Vessels with Improved Generative Adversarial Network 42

Fog Images Generation About Unmanned Surface Vessels with Im...

引用

42nd Chinese Control Conference, CCC 2023

作者： Tang, Yifeng Huang, Zhihui Tang, Chuancong Luo, Chuanshang Xu, Yifan Liu, Bin Zhang, Hai-Tao School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789887581543

This paper proposes a fog weather data augmentation method for the unmanned surface vessels (USVs) via improved Generative Adversarial Network(GAN) model. First, a generator scheme for GAN is proposed with the guided generation of the atmospheric scattering model in this paper. A Laplacian Pyramid Based Depth Residuals model is added to the generator which reduces the difficulty of generating fog images caused by the degradation of water surface image and improves the quality of generated images. Finally, fog images are generated from sunny weather images collected with HUST-12C by LPBDR-GAN model and experiments show that generated images are very close to real fog images. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Generative adversarial networks

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：