检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chen, Kecheng Li, Haoliang Yan, Hong City University of Hong Kong Department of Electrical Engineering Center for Intelligent Multidimensional Data Analysis Kowloon Hong Kong

ISBN: (纸本)9781728163277

Recently, successive subspace learning (SSL)-based methods have shown to be effective for the task of visual object classification with mild data desire and mathematically transparent interpretable capability. However, existing SSL-based methods rely heavily on the data-centric subspace representations, leading to potential performance degradation problem in case of the domain shift between the training (a.k.a., source domain) and testing (a.k.a., target domain) data. To address this limitation, we propose an effective successive subspace learning method based on existing SSL-based methods. Specifically, we introduce a novel linear transformation layer to align eigenvectors in SSL module between source and target domains, as such, the discrepancy between source and target domains will be reduced, resulting in better cross-domain performance. The effectiveness of our proposed method is demonstrated on the Office-Caltech-10 and Office-31 benchmark datasets by using features extracted from pre-trained deep neural networks as input. © 2023 IEEE.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

3D Cellular Segmentation of Live Embryos via Topologically and Biologically Boundary-aware Semi-supervised Learning

3D Cellular Segmentation of Live Embryos via Topologically a...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Zelin Huang, Zhaoke Yan, Hong City University of Hong Kong Department of Electrical Engineering Hong Kong Centre for Intelligent Multidimensional Data Analysis Hong Kong

ISBN: (纸本)9781665410205

3D cellular segmentation of fluorescence images of live embryos is a fundamental step in the analysis of embryonic developmental processes. However, existing fully supervised learning methods (CNN-based) to achieve this often suffer from non-robust loss functions and insufficient training data. Previous work on cellular segmentation did not consider topological information and biological constraints. In this paper, we propose a novel semi-supervised method using topological loss and biologically boundary-aware synthetic (labeled and unlabeled mixed) ground truth for 3D cellular segmentation of live embryos. The topological loss function guides the model to extract features in latent space. Semi-supervised learning and synthetic datasets improve the accuracy of inner and outer membrane recognition on a large number of unlabeled images. Experiment results and evaluation on 1472 live embryo images show that our method outperforms existing deep-learning models. This method can be adapted to images of live embryos of other animals. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exposing Computer-Generated Images Via Amplified Texture Differences Learning

Exposing Computer-Generated Images Via Amplified Texture Dif...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Xu, Qiang Wang, Zhe Mi, Zhongjie Yan, Hong Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Department of Electrical Engineering Kowloon Hong Kong Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Department of Advanced Design and Systems Engineering Hong Kong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350337020

Many Computer-Generated (CG) images are spreading widely on the Internet, which may deliberately misinform or deceive the public. Therefore, distinguishing CG images from natural photographic (PG) has become a frontier research topic in the field of image forensics. Although many algorithms have been proposed, it is still very challenging to detect CG images generated by the recent cutting-edge generative methods. Besides, most existing algorithms tend to generalize poorly when facing different unseen multimodal generative models. To address this issue, a novel method based on amplified texture differences learning is proposed to tackle this problem. We first design a deep texture enhancement module for discriminative texture amplification. Specifically, a semantic segmentation module is utilized to generate semantic segmentation map for the affine transformation operation guidance, which can be further used to recover the texture in different regions of the input image. Then, the combination of the original image and the high-frequency components of the original and enhanced images are fed into a hybrid neural network equipped with attention mechanisms, which refines intermediate features and facilitates trace exploration in spatial and channel dimensions respectively. By verifying on several commonly used benchmark datasets and a newly constructed dataset11The benchmark is available at https://***/191578010/DSGCG. with more realistic and diverse images, the experimental results demonstrate that the proposed approach outperforms some existing methods. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Quaternions and Dual Quaternion Vectors

引用

Communications on Applied Mathematics and Computation 2022年第4期4卷 1494-1508页

作者： Liqun Qi Chen Ling Hong Yan Department of Mathematics School of ScienceHangzhou Dianzi UniversityHangzhou 310018ZhejiangChina Department of Applied Mathematics The Hong Kong Polytechnic UniversityHung HomKowloonHong KongChina Department of Electrical Engineering and Centre for Intelligent Multidimensional Data Analysis City University of Hong KongKowloonHong KongChina

We introduce a total order and an absolute value function for dual *** absolute value function of dual numbers takes dual number values,and has properties similar to those of the absolute value function of real *** define the magnitude of a dual quaternion,as a dual *** upon these,we extend 1-norm,co-norm,and 2-norm to dual quaternion vectors.

关键词： Dual number Absolute value function Dual quaternion Magnitude Norm

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Object Classification Via Successive Subspace Alignment

Cross-Domain Object Classification Via Successive Subspace A...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kecheng Chen Haoliang Li Hong Yan Department of Electrical Engineering and Center for Intelligent Multidimensional Data Analysis City University of Hong Kong Kowloon Hong Kong SAR

关键词： Training Learning systems Degradation Deep learning Visualization Neural networks Signal processing

来源：评论

学校读者我要写书评

暂无评论

A Research of a Modified Bearing Fault Diagnosis Model Based on Deformable Atrous Convolution and Squeeze-and-Excitation Aggregation 13

A Research of a Modified Bearing Fault Diagnosis Model Based...

引用

13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022

作者： Yu, Y. Chen, Z.Y. Fang, X. Zhang, D.C. Wang, Z. School of Mechanical Engineering Sichuan University Chengdu China City University of Hong Kong Hong Kong and Center for Intelligent Multidimensional Data Analysis Hong Kong Science Park Department of Advanced Design and Systems Engineering Shatin Hong Kong

ISBN: (数字)9781665486903

ISBN: (纸本)9781665486903

In order to accurately and intelligently identify the fault signal characteristics of bearing in modern rotating machinery industries, a comprehensive novel fault diagnosis model is introduced by using a few data points as input signals. In this paper, the main methods of the model are processing the two signal inputs, frequency-domain signal (FDS) and time-frequency graph (TFG), into a network built up with convolution (Conv) and deformable atrous Conv. Then, this network extracts their features respectively. After squeezing-and-excitation aggregation on the features, three types of outputs are obtained for tasks of faulty bearing position detection, fault type diagnosis, and damage size estimation. This method allows the fault diagnosis of different locations, fault types, and fault degrees to be completed simultaneously, and the state-of-Art effect can be achieved. Two bearing vibration signal datasets are used in the paper to evaluate the performance of the model, and experimental results prove an effective multi-task fault diagnosis ability on the three tasks. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

RO-SVD: A Reconfigurable Hardware Copyright Protection Framework for AIGC Applications

arXiv

引用

arXiv 2024年

作者： Ran, Zhuoheng Abdelgawad, Muhammad A.A. Zhang, Zekai Cheung, Ray C.C. Yan, Hong Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Hong Kong

The dramatic surge in the utilisation of generative artificial intelligence (GenAI) underscores the need for a secure and efficient mechanism to responsibly manage, use and disseminate multi-dimensional data generated by artificial intelligence (AI). In this paper, we propose a blockchain-based copyright traceability framework called ring oscillator-singular value decomposition (RO-SVD), which introduces decomposition computing to approximate low-rank matrices generated from hardware entropy sources and establishes an AI-generated content (AIGC) copyright traceability mechanism at the device level. By leveraging the parallelism and reconfigurability of field-programmable gate arrays (FPGAs), our framework can be easily constructed on existing AI-accelerated devices and provide a low-cost solution to emerging copyright issues of AIGC. We developed a hardware-software (HW/SW) co-design prototype based on comprehensive analysis and on-board experiments with multiple AI-applicable FPGAs. Using AI-generated images as a case study, our framework demonstrated effectiveness and emphasised customisation, unpredictability, efficiency, management and reconfigurability. To the best of our knowledge, this is the first practical hardware study discussing and implementing copyright traceability specifically for AI-generated content. Copyright © 2024, The Authors. All rights reserved.

关键词： Reconfigurable hardware

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network and Superpixel Based Brain Tissue Segmentation (Corrected Version)

arXiv

引用

arXiv 2022年

作者： Wu, Chong Feng, Zhenan Zhang, Houwang Yan, Hong Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Kowloon Hong Kong

Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG. Copyright © 2022, The Authors. All rights reserved.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

A survey of superpixel methods and their applications

TechRxiv

引用

TechRxiv 2024年

作者： Wu, Chong Yan, Hong Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Kowloon Hong Kong

Superpixels can preserve the structure and reduce the redundancy of the original image. Because of these advantages, superpixel generation or superpixel segmentation is widely used as a pre-processing step in many image processing tasks. Although superpixels can be employed to reduce computational complexity, some challenges, such as the non-Euclidean feature learning problem introduced by superpixels, still exist. This survey provides a comprehensive overview of the state-of-the-art superpixel methods, major challenges, commonly used evaluation metrics, applications of superpixels, and potential future directions for the study of superpixels. We first give a review of the state-of-the-art superpixel methods. Next, we use different evaluation metrics to evaluate the performance of 25 up-to-date superpixel methods on different datasets in different noisy environments. After that, we introduce several up-to-date applications of superpixels. Finally, we give several possible future directions for addressing the challenges of superpixels. © 2024, CC BY.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

RO-SVD: A Reconfigurable Hardware Copyright Protection Framework for AIGC Applications

RO-SVD: A Reconfigurable Hardware Copyright Protection Frame...

引用

International Conference on Application Specific Systems (ASAP), Architectures and Processors

作者： Zhuoheng Ran Muhammad A.A. Abdelgawad Zekai Zhang Ray C.C. Cheung Hong Yan Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Hong Kong SAR China

ISBN: (数字)9798350349634

ISBN: (纸本)9798350349641

The dramatic surge in the utilisation of generative artificial intelligence (GenAI) underscores the need for a secure and efficient mechanism to responsibly manage, use and disseminate multidimensional data generated by artificial intelligence (AI). In this paper, we propose a blockchain-based copyright traceability framework called ring oscillator-singular value decomposition (RO-SVD), which introduces decomposition computing to approximate low-rank matrices generated from hardware entropy sources and establishes an AI-generated content (AIGC) copyright traceability mechanism at the device level. By leveraging the parallelism and reconfigurability of field-programmable gate arrays (FPGAs), our framework can be easily constructed on existing AI -accelerated devices and provide a low-cost solution to emerging copyright issues of AIGC. We developed a hardware-software (HW /SW) co-design prototype based on comprehensive analysis and on-board experiments with multiple AI-applicable FPGAs. Using AI-generated images as a case study, oyr framework demonstrated effectiveness and emphasised customisation, unpredictability, efficiency, manage-ment and reconfigurability. To the best of our knowledge, this is the first practical hardware study discussing and implementing copyright traceability specifically for AI -generated conten t.

关键词： Program processors Generative AI Systems architecture Surge protection Prototypes Parallel processing Hardware

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：