检索结果-内蒙古大学图书馆

Multi-scale anatomical regularization for domain-adaptive segmentation of pelvic CBCT images

MEDICAL PHYSICS 2024年第12期51卷 8804-8813页

作者： Chen, Xu Pang, Yunkui Yap, Pew-Thian Lian, Jun Huaqiao Univ Coll Comp Sci & Technol Xiamen Fujian Peoples R China Huaqiao Univ Fujian Prov Univ Key Lab Comp Vis & Machine Learning Xiamen Fujian Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Fujian Peoples R China Univ North Carolina Dept Comp Sci Chapel Hill NC USA Univ North Carolina Dept Radiol Chapel Hill NC 27599 USA Univ North Carolina Biomed Res Imaging Ctr Chapel Hill NC 27599 USA Univ North Carolina Dept Radiat Oncol Chapel Hill NC 27599 USA

BackgroundCone beam computed tomography (CBCT) image segmentation is crucial in prostate cancer radiotherapy, enabling precise delineation of the prostate gland for accurate treatment planning and delivery. However, the poor quality of CBCT images poses challenges in clinical practice, making annotation difficult due to factors such as image noise, low contrast, and organ *** objective of this study is to create a segmentation model for the label-free target domain (CBCT), leveraging valuable insights derived from the label-rich source domain (CT). This goal is achieved by addressing the domain gap across diverse domains through the implementation of a cross-modality medical image segmentation *** approach introduces a multi-scale domain adaptive segmentation method, performing domain adaptation simultaneously at both the image and feature levels. The primary innovation lies in a novel multi-scale anatomical regularization approach, which (i) aligns the target domain feature space with the source domain feature space at multiple spatial scales simultaneously, and (ii) exchanges information across different scales to fuse knowledge from multi-scale *** and qualitative experiments were conducted on pelvic CBCT segmentation tasks. The training dataset comprises 40 unpaired CBCT-CT images with only CT images annotated. The validation and testing datasets consist of 5 and 10 CT images, respectively, all with annotations. The experimental results demonstrate the superior performance of our method compared to other state-of-the-art cross-modality medical image segmentation methods. The Dice similarity coefficients (DSC) for CBCT image segmentation results is 74.6 +/- 9.3$74.6 \pm 9.3$ %, and the average symmetric surface distance (ASSD) is 3.9 +/- 1.8mm$3.9\pm 1.8\;\mathrm{mm}$. Statistical analysis confirms the statistical significance of the improvements achieved by our *** method exhibits

关键词： anatomical regularization medical image segmentation unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Reversible Adversarial Examples with Minimalist Evolution for recognition Control in computer vision

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷 1142-1142页

作者： Yang, Shilong Leng, Lu Chang, Ching-Chun Chang, Chin-Chen Nanchang Hangkong Univ Jiangxi Prov Key Lab Image Proc & Pattern Recognit Nanchang 330063 Peoples R China Feng Chia Univ Informat & Commun Secur Res Ctr Taichung 407102 Taiwan Feng Chia Univ Informat Engn & Comp Sci Taichung 407102 Taiwan

As artificial intelligence increasingly automates the recognition and analysis of visual content, it poses significant risks to privacy, security, and autonomy. computer vision systems can surveil and exploit data without consent. With these concerns in mind, we introduce a novel method to control whether images can be recognized by computer vision systems using reversible adversarial examples. These examples are generated to evade unauthorized recognition, allowing only systems with permission to restore the original image by removing the adversarial perturbation with zero-bit error. A key challenge with prior methods is their reliance on merely restoring the examples to a state in which they can be correctly recognized by the model;however, the restored images are not fully consistent with the original images, and they require excessive auxiliary information to achieve reversibility. To achieve zero-bit error restoration, we utilize the differential evolution algorithm to optimize adversarial perturbations while minimizing distortion. Additionally, we introduce a dual-color space detection mechanism to localize perturbations, eliminating the need for extra auxiliary information. Ultimately, when combined with reversible data hiding, adversarial attacks can achieve reversibility. Experimental results demonstrate that the PSNR and SSIM between the restored images by the method and the original images are infinity and 1, respectively. The PSNR and SSIM between the reversible adversarial examples and the original images are 48.32 dB and 0.9986, respectively. compared to state-of-the-art methods, the method maintains high visual fidelity at a comparable attack success rate.

关键词： data security reversible data hiding reversible adversarial example dual-color space black-box attack

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Domain Alignment Learning for Single Image Dehazing

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第11期53卷 7238-7250页

作者： Dong, Yu Li, Yunan Dong, Qian Zhang, He Chen, Shifeng Shenzhen Inst Adv Technol Chinese Acad Sci Shenzhen Key Lab Comp Vis & Pattern Recognit Shenzhen Peoples R China Univ Chinese Acad Sci Shenzhen Inst Adv Technol Beijing 101408 Peoples R China Xidian Univ Sch Comp Sci & Technol Key Lab Big Data & Intelligent Vis Xian 710071 Peoples R China Xidian Univ Xian Key Lab Big Data & Intelligent Vis Xian 710071 Peoples R China Harbin Inst Technol Shenzhen Sch Mech Engn & Automation Shenzhen 518055 Peoples R China Adobe Inc San Jose CA USA

Convolutional neural networks (CNNs) have attracted much research attention and achieved great improvements in single-image dehazing. However, previous learning-based dehazing methods are mainly trained on synthetic data, which greatly degrades their generalization capability on natural hazy images. To address this issue, this article proposes a semi-supervised learning approach for single-image dehazing, where both synthetic and realistic images are leveraged during training. Considering the situation that it is hard to obtain the realistic pairs of hazy and haze-free images, how to utilize the realistic data is not a trivial work. In this article, a domain alignment module is introduced to narrow the distribution distance between synthetic data and realistic hazy images in a latent feature space. Meanwhile, a haze-aware attention module is designed to describe haze densities of different regions in the image, thus adaptively responds for different hazy areas. Furthermore, the dark channel prior is introduced to the framework to improve the quality of the unsupervised learning results by considering the statistical characters of haze-free images. Such a semi-supervised design can significantly address the domain shift issue between the synthetic and realistic data, and improve generalization performance in the real world. Experiments indicate that the proposed method obtains state-of-the-art performance on both public synthetic and realistic hazy images with better visual results.

关键词： Dehazing domain alignment haze-aware attention semi-supervised

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks in Point Clouds: A Survey

引用

REMOTE SENSING 2024年第14期16卷 2518页

作者： Li, Dilong Lu, Chenghui Chen, Ziyi Guan, Jianlong Zhao, Jing Du, Jixiang Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Key Lab Data Secur & Blockchain TechnolCol Xiamen 361021 Peoples R China

With the advancement of 3D sensing technologies, point clouds are gradually becoming the main type of data representation in applications such as autonomous driving, robotics, and augmented reality. Nevertheless, the irregularity inherent in point clouds presents numerous challenges for traditional deep learning frameworks. Graph neural networks (GNNs) have demonstrated their tremendous potential in processing graph-structured data and are widely applied in various domains including social media data analysis, molecular structure calculation, and computer vision. GNNs, with their capability to handle non-Euclidean data, offer a novel approach for addressing these challenges. Additionally, drawing inspiration from the achievements of transformers in natural language processing, graph transformers have propelled models towards global awareness, overcoming the limitations of local aggregation mechanisms inherent in early GNN architectures. This paper provides a comprehensive review of GNNs and graph-based methods in point cloud applications, adopting a task-oriented perspective to analyze this field. We categorize GNN methods for point clouds based on fundamental tasks, such as segmentation, classification, object detection, registration, and other related tasks. For each category, we summarize the existing mainstream methods, conduct a comprehensive analysis of their performance on various datasets, and discuss the development trends and future prospects of graph-based methods.

关键词： graph neural networks point cloud processing graph convolutional neural network graph attention graph-based methods classification segmentation registration object detection

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning of Intrinsic Semantics With Diffusion Model for Person Re-Identification

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 6705-6719页

作者： Tao, Xuefeng Kong, Jun Jiang, Min Lu, Ming Mian, Ajmal Jiangnan Univ Key Lab Adv Proc Control Light Ind Minist Educ Wuxi 214122 Peoples R China Jiangnan Univ Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi 214122 Peoples R China Univ Western Australia Dept Comp Sci Crawley WA 6009 Australia

Unsupervised person re-identification (Re-ID) aims to learn semantic representations for person retrieval without using identity labels. Most existing methods generate fine-grained patch features to reduce noise in global feature clustering. However, these methods often compromise the discriminative semantic structure and overlook the semantic consistency between the patch and global features. To address these problems, we propose a Person Intrinsic Semantic Learning (PISL) framework with diffusion model for unsupervised person Re-ID. First, we design the Spatial Diffusion Model (SDM), which performs a denoising diffusion process from noisy spatial transformer parameters to semantic parameters, enabling the sampling of patches with intrinsic semantic structure. Second, we propose the Semantic Controlled Diffusion (SCD) loss to guide the denoising direction of the diffusion model, facilitating the generation of semantic patches. Third, we propose the Patch Semantic Consistency (PSC) loss to capture semantic consistency between the patch and global features, refining the pseudo-labels of global features. comprehensive experiments on three challenging datasets show that our method surpasses current unsupervised Re-ID methods. The source code will be publicly available at https://***/taoxuefong/Diffusion-reid

关键词： Semantics Transformers Diffusion models Noise reduction Diffusion processes Noise measurement computational modeling Cameras Adaptation models Identification of persons Unsupervised person re-identification spatial diffusion model semantic controlled diffusion loss patch semantic consistency loss

来源：评论

学校读者我要写书评

暂无评论

Multi-label feature selection based on label distribution and neighborhood rough set

引用

NEUROcompUTING 2023年第1期524卷 142-157页

作者： Liu, Jinghua Lin, Yaojin Ding, Weiping Zhang, Hongbo Wang, Cheng Du, Jixiang Huaqiao Univ Dept Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China Minnan Normal Univ Key Lab Data Sci & Intelligence Applicat Zhangzhou 363000 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China

Multi-label feature selection is an indispensable technology in multi-semantic high-dimensional data preprocessing, which has been brought into focus in recent years. However, most existing methods explicitly assume that the significance of all relevant labels is the same for every instance, while ignoring the real scenarios that the significance of available labels to each instance is usually different. In this paper, we propose a novel multi-label feature selection based on label distribution and neighborhood rough set, known as LDRS. To be specific, we first construct a label enhancement method based on instance information distribution to convert the logical labels of multi-label data into label distribution, thereby capturing label significance to provide additional information for learning tasks. Then, we extend the neighborhood rough set model for label distribution learning, and discuss the related properties in detail. This extended model can effectively avoid the selection of neighborhood granularity and seamlessly apply to handle label distribution data. After that, two feature significance measures are established to realize the quality evaluation of features and the fusion of label-specific features. Finally, a novel feature selection framework is designed, which takes into account feature significance, label significance, and label-specific features, simultaneously. Experiments on both public and real-world datasets exhibit the advantages of the proposed method. (c) 2022 Published by Elsevier B.V.

关键词： Multi-label learning Feature selection Neighborhood rough set label distribution

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Inversion Method for Airborne Time-Domain Electromagnetic Data Using Convolutional Neural Network

引用

APPLIED SCIENCES-BASEL 2024年第19期14卷 8883页

作者： Yu, Xiaodong Zhang, Peng Yu, Xi Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China Chengdu Univ Technol Coll Comp Sci & Cyber Secur Chengdu 610059 Peoples R China

Due to the high detection efficiency of the airborne time-domain electromagnetic method, it can quickly collect electromagnetic response data for large area-wide regions, but it also brings great challenges to the inversion interpretation of the data because there are numerous survey data that need to be inverted. Conventional optimal inversion and fast imaging methods still take a long time to obtain conductivity and depth information, which affect the efficiency of real-time data interpretation. In this paper, we present a deep learning inversion method that can be used to solve the fast inversion problem of airborne time-domain electromagnetic data;the method uses a one-dimensional convolutional neural network. The network structure consists of two parts containing different numbers of convolutional and pooling layers. The training sample dataset was generated via two ways of constructing geoelectric models through forward modelling. To check the effectiveness of our deep learning inversion strategy, we tested it on synthetic data and two types of survey data. The experimental results show that this inversion method is effective and that it can be applied to airborne time-domain electromagnetic data collected using different observation systems. The proposed inversion method can obtain better inversion results for both simple and complex stratigraphic structures and requires significantly less computation time compared to conventional optimal inversion methods.

关键词： deep learning fast inversion airborne time-domain electromagnetic convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

Generate Like Experts: Multi-Stage Font Generation by Incorp...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Fu, Bin Yu, Fanghua Liu, Anran Wang, Zixuan Wen, Jie He, Junjun Qiao, Yu Chinese Acad Sci Shenzhen Inst Adv Technol ShenZhen Key Lab Comp Vis & Pattern Recognit Shenzhen Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China Univ Hong Kong Hong Kong Peoples R China Harbin Inst Technol Shenzhen Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Few-shot font generation (FFG) produces stylized font images with a limited number of reference samples, which can significantly reduce labor costs in manual font designs. Most existing FFG methods follow the style-content disentanglement paradigm and employ the Generative Adversarial Network (GAN) to generate target fonts by combining the decoupled content and style representations. The complicated structure and detailed style are simultaneously generated in those methods, which may be the sub-optimal solutions for FFG task. Inspired by most manual font design processes of expert designers, in this paper, we model font generation as a multi-stage generative process. Specifically, as the injected noise and the data distribution in diffusion models can be well-separated into different sub-spaces, we are able to incorporate the font transfer process into these models. Based on this observation, we generalize diffusion methods to model font generative process by separating the reverse diffusion process into three stages with different functions: The structure construction stage first generates the structure information for the target character based on the source image, and the font transfer stage subsequently transforms the source font to the target font. Finally, the font refinement stage enhances the appearances and local details of the target font images. Based on the above multi-stage generative process, we construct our font generation framework, named MSD-Font, with a dual-network approach to generate font images. The superior performance demonstrates the effectiveness of our model. The code is available at: https://***/fubinfb/MSD-Font

关键词： Diffusion Model Few-shot Font Generation Probabilistic Generative Model

来源：评论

学校读者我要写书评

暂无评论

Bifurcation analysis, stationary optical solitons and exact solutions for generalized nonlinear Schrodinger equation with nonlinear chromatic dispersion and quintuple power-law of refractive index in optical fibers

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2023年 615卷

作者： Han, Tianyong Li, Zhao Li, Chenyu Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Sichuan Normal Univ VC & VR Key Lab Sichuan Prov Chengdu 610068 Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China

In this paper, the bifurcation, stationary optical solitons and exact solutions in optical fiber propagation are studied. The propagation model is described by a generalized non-linear Schrodinger equation with Kudryashov's quintuple power law of refractive index. First, the equation is transformed into a second-order nonlinear ordinary differential equation by an appropriate transformation. Then, the bifurcation of the phase diagram of the obtained ordinary differential equation is established using planar dynamic system theory, and the types of optical solitons and exact solutions are determined. What is more, the stationary optical solitons and exact solutions are obtained by the polynomial complete discriminant system, and are demonstrated in 3D and 2D graphics by using the symbolic computation software Maple. Finally, the obtained stationary optical solitons and exact solutions include the Jacobi elliptic function solution, hyperbolic function solution, rational function solution, trigonometric function solution and exponential function solution. Moreover, the results provide a method to further study stationary optical solitons and exact solutions of propagation pulses in optical fibers.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Stationary optical soliton Exact solution Bifurcation Nonlinear chromatic dispersion Quintuple power-law of refractive index

来源：评论

学校读者我要写书评

暂无评论

DGSD: Dynamical graph self-distillation for EEG-based auditory spatial attention detection

引用

NEURAL NETWORKS 2024年 179卷 106580页

作者： Fan, Cunhang Zhang, Hongyu Huang, Wei Xue, Jun Tao, Jianhua Yi, Jiangyan Lv, Zhao Wu, Xiaopei Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China Tsinghua Univ Dept Automat Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China

Auditory Attention Detection (AAD) aims to detect the target speaker from brain signals in a multi-speaker environment. Although EEG-based AAD methods have shown promising results in recent years, current approaches primarily rely on traditional convolutional neural networks designed for processing Euclidean data like images. This makes it challenging to handle EEG signals, which possess non-Euclidean characteristics. In order to address this problem, this paper proposes a dynamical graph self-distillation (DGSD) approach for AAD, which does not require speech stimuli as input. Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals. In addition, to further improve AAD detection performance, self-distillation, consisting of feature distillation and hierarchical distillation strategies at each layer, is integrated. These strategies leverage features and classification results from the deepest network layers to guide the learning of shallow layers. Our experiments are conducted on two publicly available datasets, KUL and DTU. Under a 1-second time window, we achieve results of 90.0% and 79.6% accuracy on KUL and DTU, respectively. We compare our DGSD method with competitive baselines, and the experimental results indicate that the detection performance of our proposed DGSD method is not only superior to the best reproducible baseline but also significantly reduces the number of trainable parameters by approximately 100 times.

关键词： Auditory attention detection Electroencephalography (EEG) Dynamical graph convolutional network Self-distillation Frequency domain

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：