检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350374889

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (Sa S) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all Sa S probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. © 2024 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Analysis of multimodal fusion strategies in deep learning for ischemic stroke lesion segmentation on computed tomography perfusion data

引用

Multimedia Tools and Applications 2025年第10期84卷 7493-7518页

作者： Raju, Chintha Sri Pothu Neelapu, Bala Chakravarthy Laskar, Rabul Hussain Muhammad, Ghulam Speech and Image Processing Lab Department of ECE National Institute of Technology Silchar Assam Silchar788010 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia

Stroke poses a significant risk to human life. Segmenting and immediately treating the stroke core stops its further development, therefore, enhancing the likelihood of survival. Convolutional neural networks (CNN) have been very successful in medical image segmentation, namely in the field of deep learning, and have produced the most advanced outcomes. Multi-modal images provide superior outcomes in the segmentation of stroke lesions compared to single-modal images. The integration of input from several modalities at various levels is crucial in determining performance and producing diverse outcomes in deep learning models that use multimodalities. Further investigation is required to explore the optimal methods for processing multimodal data in CNNs, the influence of fusion on CNN learning, and the effect of fusion strategies on lesions of varying sizes. To examine the impact of a multi-modal fusion method on lesion segmentation, we assessed four models using distinct fusion techniques, including early, late, bottleneck, and hierarchical fusions. This study discusses the various fusion procedures used in segmenting the lesion using computed tomography perfusion data. In addition, both quantitative and qualitative assessments, including deep feature analysis and feature similarity, were conducted to assess the impact of the fusion technique on the model’s performance. Furthermore, we examined the influence of fusion techniques on the size of the lesion. In addition, we analyzed the advantages and disadvantages of several multi-modal fusion systems. Our findings demonstrate that the bottleneck fusion technique got the highest dice score, 0.582, on the Ischemic Stroke Lesion Segmentation 2018 validation data as a result of its capacity to construct complex relationships across several modalities. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising 22

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350345346

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional auto encoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional auto encoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and de noising. The models trained on the MNIST handwritten-digit and CIFAR-IO image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%. © 2023 IEEE.

关键词： autoencoders bidirectional au-toencoders Bidirectional backpropagation bidirectional networks large language models variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

GAN-DIRNet:A Novel Deformable image Registration Approach for Multimodal Histological images

引用

computers, Materials & Continua 2024年第7期80卷 487-506页

作者： Haiyue Li Jing Xie Jing Ke Ye Yuan Xiaoyong Pan Hongyi Xin Hongbin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai200240China Department of Pathology Ruijin HospitalShanghai Jiao Tong UniversitySchool of MedicineShanghai200025China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai200240China Global Institute of Future Technology Shanghai Jiao Tong UniversityShanghai200240China

Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of *** neural network(CNN)and generative adversarial network(GAN)are pivotal inmedical image ***,existing methods often struggle with severe interference and deformation,as seen in histological images of conditions like Cushing’s *** argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator *** this study,we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image *** begin with,the discriminators of two GANs are embedded as a new dual parallel feature extraction module into the unsupervised registration networks,characterized by implicitly extracting feature descriptors of specific ***,modal feature description layers and registration layers collaborate in unsupervised optimization,facilitating faster convergence and more precise ***,experiments and evaluations were conducted on the registration of the Mixed National institute of Standards and Technology database(MNIST),eight publicly available datasets of histological sections and the Clustering-Registration-Classification-Segmentation(CRCS)dataset on the Cushing’s *** results demonstrate that our proposed GAN-DIRNet method surpasses existing approaches like DIRNet in terms of both registration accuracy and time efficiency,while also exhibiting robustness across different image types.

关键词： Histological images registration deformable registration generative adversarial network cushing’s disease machine learning computer vision

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Training Deep Neural Classifiers with Soft Diamond Regularizers

Training Deep Neural Classifiers with Soft Diamond Regulariz...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable $(\mathcal{S}\alpha \mathcal{S})$ bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all $\mathcal{S}\alpha \mathcal{S}$ probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed $L_{2}$ regularizers on all the test cases. Soft diamond regularizers also outperformed $L_{1}$ lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization.

关键词： Training Accuracy Sparse approximation Stars Tail Machine learning Probability density function Diamond Table lookup Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Simulation of microstructures and machine learning

arXiv

引用

arXiv 2025年

作者： Schladitz, Katja Redenbach, Claudia Barisin, Tin Jung, Christian Jeziorski, Natascha Bosnar, Lovro Fulir, Juraj Gospodnetić, Petra Fraunhofer ITWM Image Processing Kaiserslautern Germany RPTU Department of Mathematics Kaiserslautern Germany RPTU Department of Mathematics Germany RPTU Department of Computer Science Germany

Machine learning offers attractive solutions to challenging image processing tasks. Tedious development and parametrization of algorithmic solutions can be replaced by training a convolutional neural network or a random forest with a high potential to generalize. However, machine learning methods rely on huge amounts of representative image data along with a ground truth, usually obtained by manual annotation. Thus, limited availability of training data is a critical bottleneck. We discuss two use cases: optical quality control in industrial production and segmenting crack structures in 3D images of concrete. For optical quality control, all defect types have to be trained but are typically not evenly represented in the training data. Additionally, manual annotation is costly and often inconsistent. It is nearlyMSC Codes 60D05 © 2025, CC BY-NC-ND.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Metric Identification of Vertices in Polygonal Cacti

引用

computer Modeling in Engineering & Sciences 2023年第7期136卷 883-899页

作者： Xiujun Zhang Muhammad Salman Anam Rani Rashna Tanveer Usman Ali Zehui Shao School of Computer Science Chengdu UniversityChengduChina Department of Mathematics The Islamia University of BahawalpurBahawalpurPakistan Centre for Advanced Studies in Pure and Applied Mathematics Bahauddin Zakariya UniversityMultanPakistan Institute for Intelligent Information Processing South China Business College of Guangdong University of Foreign StudiesGuangzhouChina

The distance between two vertices u and v in a connected graph G is the number of edges lying in a shortest path(geodesic)between them.A vertex x of G performs the metric identification for a pair(u,v)of vertices in G if and only if the equality between the distances of u and v with x implies that u=v(That is,the distance between u and x is different from the distance between v and x).The minimum number of vertices performing the metric identification for every pair of vertices in G defines themetric dimension of *** this paper,we performthemetric identification of vertices in two types of polygonal cacti:chain polygonal cactus and star polygonal cactus.

关键词： Metric metric identification metric generator metric dimension cactus graph

来源：评论

学校读者我要写书评

暂无评论

Speed Bump Detection Through Inertial Sensors and Deep Learning in a Multi-contextual Analysis

引用

SN computer Science 2023年第1期4卷 18页

作者： Menegazzo, Jeferson von Wangenheim, Aldo Graduate Program in Computer Science (PPGCC) Image Processing and Computer Graphics Lab (LAPIX) Brazilian National Institute for Digital Convergence (INCoD) Department of Informatics and Statistics (INE) Federal University of Santa Catarina (UFSC)-Florianópolis Santa Catarina Brazil

Speed bumps are vertical raisings of the road pavement used to force drivers to slow down to ensure greater safety in traffic. However, these obstacles have disadvantages in terms of efficiency and safety, where the presence of speed bumps can affect travel time and fuel consumption, cause traffic jams, delay emergency vehicles, and cause vehicle damage or accidents when not properly signaled. Due to these factors, the availability of geolocation information for these obstacles can benefit several applications in Intelligent Transportation System (ITS), such as Advanced Driver Assistance Systems (ADAS) and autonomous vehicles, allowing to trace more efficient routes or alert the driver of the presence of the obstacle ahead. Speed bump detection applications described in the literature employ cameras or inertial sensors, represented by accelerometers and gyroscopes. While camera-based solutions are mature with evaluation in different contextual conditions, those based on inertial sensors do not offer multi-contextual analyses, being mostly simple applications of proof of concept, not applicable in real-world scenarios. For this reason, in this work, we propose the development of a reliable speed bump detection model based on inertial sensors, capable of operating reliably in contextual variations: different vehicles, driving styles, and environments in which vehicles can travel to. For the model development and validation, we collect nine datasets with contextual variations, using three different vehicles, with three different drivers, in three different environments, in which there are three different surface types, in addition to variations in conservation state and the presence of obstacles and anomalies. The speed bumps are present in two different pavement types, asphalt and cobblestone. We use the collected data in experiments to evaluate aspects such as the influence of the placement of the sensors for vehicle data collection and the data window size. Afterwar

关键词： Autonomous vehicles Deep learning Inertial sensors Intelligent transport systems Road conditions Speed bump

来源：评论

学校读者我要写书评

暂无评论

Caustics of developable surfaces

引用

Frontiers of Information Technology & Electronic Engineering 2022年第3期23卷 479-487页

作者： Miklos HOFFMANN Imre JUHASZ Ede TROLL Institute of Mathematics and Computer Science Eszterhazy Karoly UniversityEger 3300Hungary Department of Computer Graphics and Image Processing University of DebrecenDebrecen 4010Hungary Department of Descriptive Geometry University of MiskolcMiskolc 3515Hungary

While considering a mirror and light rays coming either from a point source or from infinity,the reflected light rays may have an envelope,called a caustic *** this paper,we study developable surfaces as *** caustic surfaces,described in a closed form,are also developable surfaces of the same type as the original mirror *** provide efficient,algorithmic computation to find the caustic surface of each of the three types of developable surfaces(cone,cylinder,and tangent surface of a spatial curve).We also provide a potential application of the results in contemporary free-form architecture design.

关键词： Caustics Developable surface Reflected light rays Curve of regression

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：