检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhao, Wenzhao Wichtmann, Barbara D. Albert, Steffen Maurer, Angelika Zöllner, Frank G. Attenberger, Ulrike Hesser, Jürgen Interdisciplinary Center for Scientific Computing Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany Department of Diagnostic and Interventional Radiology University Hospital Bonn Germany Computer Assisted Clinical Medicine Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany Interdisciplinary Center for Scientific Computing Central Institute for Computer Engineering CSZ Heidelberg Center for Model-Based AI Data Analysis and Modeling in Medicine Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany

group-equivariant convolutional neural networks (G-CNN) heavily rely on parameter sharing to increase CNN’s data efficiency and performance. However, the parameter-sharing strategy greatly increases the computational burden for each added parameter, which hampers its application to deep neural network models. In this paper, we address these problems by proposing a non-parameter-sharing approach for group equivariant neural networks. The proposed methods adaptively aggregate a diverse range of filters by a weighted sum of stochastically augmented decomposed filters. We give theoretical proof about how the continuous group convolution can be approximated by our methods. Our method applies to both continuous and discrete groups, where the augmentation is implemented using Monte Carlo sampling and bootstrap resampling, respectively. We demonstrate that our methods serve as an efficient extension of standard CNN. Experiments on group equivariance tests show how our methods can achieve superior performance to parameter-sharing group equivariant networks. Experiments on image classification and image denoising tasks show that in certain scenarios, with a suitable set of filter bases, our method helps improve the performance of standard CNNs and build efficient lightweight image denoising networks. The code will be available at https://***/ZhaoWenzhao/MCG_CNN. Copyright © 2023, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

RAST: A Reward Augmented Model for Fine-Grained Sentiment Transfer 10th

RAST: A Reward Augmented Model for Fine-Grained Sentiment Tr...

引用

10th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2021

作者： Hu, Xiaoxuan Zhang, Hengtong Zhao, Wayne Xin Li, Yaliang Gao, Jing Wen, Ji-Rong School of Information Renmin University of China Beijing China School of Electrical and Computer Engineering Purdue University West Lafayette United States Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science and Engineering University at Buffalo Buffalo United States Alibaba Group Hangzhou China

ISBN: (纸本)9783030884796

In this paper, we propose a novel model RAST (Reward Augmented Sentiment Transfer) for fine-grained sentiment transfer. Existing methods usually suffer from two major drawbacks, i.e., blurre d sentiment distinction and unsatisfactory content preservation. Considering the above issues, we design two kinds of rewards to better control sentiment and content. Specially, we develop a pairwise comparative discriminator that enforces to generate sentences with clear distinctions for different sentiment intensities. Moreover, we utilize an effective sampling strategy to obtain pseudo-parallel sentences with minor changes on the input sentence to enhance content preservation. Experiments on a benchmark dataset show that the proposed model outperforms several competitive approaches. © 2021, Springer Nature Switzerland AG.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment

arXiv

引用

arXiv 2023年

作者： Chen, Kecheng Liu, Jie Wan, Renjie Lee, Victor Ho-Fun Vardhanabhuti, Varut Yan, Hong Li, Haoliang The Department of Electrical Engineering The Center for Intelligent Multidimensional Data Analysis City University of Hong Kong Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The Department of Clinical Oncology School of Clinical Medicine LKS Faculty of Medicine The University of Hong Kong Hong Kong The Department of Diagnostic Radiology School of Clinical Medicine LKS Faculty of Medicine The University of Hong Kong Hong Kong

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning is widely used in this problem, but the performance of testing data (a.k.a. target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (a.k.a. source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance. © 2023, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT 3D AFFINELY EQUIVARIANT CNNS WITH ADAPTIVE FUSION OF AUGMENTED SPHERICAL FOURIER-BESSEL BASES

arXiv

引用

arXiv 2024年

作者： Zhao, Wenzhao Albert, Steffen Wichtmann, Barbara D. Maurer, Angelika Attenberger, Ulrike Zöllner, Frank G. Hesser, Jürgen School of Information Engineering Nanjing University of Finance and Economics Interdisciplinary Center for Scientific Computing Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany Computer Assisted Clinical Medicine Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany Clinic of Neuroradiology University Hospital Bonn Germany Department of Diagnostic and Interventional Radiology University Hospital Bonn Germany Department of Biomedical Imaging and Image-guided Therapy Medical University of Vienna Austria Interdisciplinary Center for Scientific Computing Central Institute for Computer Engineering CSZ Heidelberg Center for Model-Based AI Data Analysis and Modeling in Medicine Mannheim Institute for Intelligent Systems in Medicine Medical Faculty Mannheim Heidelberg University Germany

Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these networks, which rely on parameter sharing and discrete transformation groups, often underperform in modern deep neural network architectures for processing volumetric images, such as the common 3D medical images. To address these limitations, this paper presents an efficient non-parameter-sharing continuous 3D affine group equivariant neural network for volumetric images. This network uses an adaptive aggregation of Monte Carlo augmented spherical Fourier-Bessel filter bases to improve the efficiency and flexibility of 3D group equivariant CNNs for volumetric data. Unlike existing methods that focus only on angular orthogonality in filter bases, the introduced spherical Bessel Fourier filter base incorporates both angular and radial orthogonality to improve feature extraction. Experiments on four medical image segmentation datasets show that the proposed methods achieve better affine group equivariance and superior segmentation accuracy than existing 3D group equivariant convolutional neural network layers, significantly improving the training stability and data efficiency of conventional CNN layers (at 0.05 significance level). The code is available at https://***/ZhaoWenzhao/WMCSFB. Copyright © 2024, The Authors. All rights reserved.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective

arXiv

引用

arXiv 2022年

作者： Wang, Jihong Luo, Minnan Li, Jundong Liu, Ziqi Zhou, Jun Zheng, Qinghua The Ministry of Education Key Lab for Intelligent Networks and Network Security School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China The Department of Electrical and Computer Engineering Department of Computer Science School of Data Science University of Virginia United States The Ant Financial Services Group Zhejiang Hangzhou310000 China

Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rendering them infeasible when label information is not available. A straightforward direction is to employ the widely used Infomax technique from typical Unsupervised Graph Representation Learning (UGRL) to learn robust unsupervised representations. Nonetheless, directly transplanting the Infomax technique from typical UGRL to robust UGRL may involve a biased assumption. In light of the limitation of Infomax, we propose a novel unbiased robust UGRL method called Robust Graph Information Bottleneck (RGIB), which is grounded in the Information Bottleneck (IB) principle. Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph. There are mainly two challenges to optimize RGIB: 1) high complexity of adversarial attack to perturb node features and graph structure jointly in the training procedure;2) mutual information estimation upon adversarially attacked graphs. To tackle these problems, we further propose an efficient adversarial training strategy with only feature perturbations and an effective mutual information estimator with subgraph-level summary. Moreover, we theoretically establish a connection between our proposed RGIB and the robustness of downstream classifiers, revealing that RGIB can provide a lower bound on the adversarial risk of downstream classifiers. Extensive experiments over several benchmarks and downstream tasks demonstrate the effectiveness and superiority of our proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Summarization of Videos with the Signature Transform

TechRxiv

引用

TechRxiv 2022年

作者： de Curtò, Joaquim de Zarzà, Irene Roig, Gemma Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Shatin Hong Kong Department of Computer Engineering Universitat Politècnica de València València Singapore Studies of Computer Science Multimedia and Telecommunications Universitat Oberta de Catalunya Barcelona Spain Department of Computer Science Goethe University Frankfurt Frankfurt am Main Germany

This manuscript proposes a new benchmark to assess the goodness of visual summaries without the necessity of human annotators. It is based on the Signature Transform, specifically on RMSE and MAE Signature and Log-Signature, and builds on the assumption that uniform random sampling can provide accurate summarization capabilities. First, we introduce a preliminary baseline for automatic video summarization, which has at its core a Vision Transformer, an image-text model pre-trained with contrastive learning (CLIP), as well as a module of object detection. Our baseline leverages video text descriptions to determine the most frequent nouns to use as anchors, and then it performs an open-vocabulary image search on the video frames. This enables a zero-shot text-conditioned object detection to select the frames for the final video summary. Despite not needing any proper fine-tuning, our approach provides accurate summaries on a wide range of video data. Since there are not many datasets available for this task, a new dataset consisting of videos from Youtube and the corresponding automatic audio transcriptions is provided. Then, a state-of-the-art accurate technique based on the harmonic components that the Signature Transform is able to capture, and that achieves compelling accuracy © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Reliable Method to Estimate the Bispectral Index Value Using a Single Frontal EEG Channel for Intra and Inter Subject Variability

A Reliable Method to Estimate the Bispectral Index Value Usi...

引用

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Shahbakhti, Mohammad Beiramvand, Matin Krycinska, Roza Nasiri, Erfan Chen, Wei Sole-Casals, Jordi Wierzchon, Michal Broniec-Wojcik, Anna Augustyniak, Piotr Marozas, Vaidotas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Tampere University Faculty of Information Technology and Communication Tempere Finland Jagiellonian University Medical College Doctoral School in Medical and Health Sciences Krakow Poland Jagiellonian University Collegium Medicum Department of Interdisciplinary Intensive Care Krakow Poland Allameh Tabataba'i University Faculty of Statistics Mathematics and Computer Tehran Iran Fudan University Center for Intelligent Medical Electronics School of Information Science and Technology Shanghai China University of Vic-Central University of Catalonia Data and Signal Processing Research Group Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Agh University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland

ISBN: (纸本)9781665493840

Objective: Monitoring the depth of anesthesia (DoA) plays an important role for administering the drug injection during a surgery, i.e., preventing undesired awareness and inordinate anesthetic depth. Although the bispectral index (BIS) monitor is the golden standard system for the DoA monitoring, it is still not affordable for the developing countries. Alternatively, a low-cost electroencephalogram (EEG) headband can be used. The objective of this paper is to present a new algorithm for estimating the BIS values using a single frontal EEG channel. Method: In the first step, the EEG signal is filtered for the elimination of artifacts and is split into its sub-bands. In the second step, several linear and nonlinear features are extracted from each sub-band and fed to a random forest regression model in order to estimate the BIS. The performance of the proposed algorithm is assessed using EEG data recorded from twenty-four subjects during the general anesthesia and is validated in terms of correlation coefficient (CC) and absolute error (AE) between the reference and estimated BIS values. Results: The proposed algorithm achieved the mean CC of 0.83 and AE of 6.5 for intra subject variability and mean CC of 0.87 and AE of 5.5 for inter subject variability. Significance: Given the similar results for both intra and inter subject variability, the proposed algorithm has the potential to be used in the real-world scenario. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Novel Augmented Reality-Based Simulator for Enhancing Orthopedic Surgical Training

SSRN

引用

SSRN 2024年

作者： Wu, Luohong Seibold, Matthias Cavalcanti, Nicola A. Hein, Jonas Gerth, Tatiana Lekar, Roni Hoch, Armando Vlachopoulos, Lazaros Grabner, Helmut Zingg, Patrick Farshad, Mazda Fürnstahl, Philipp Research in Orthopedic Computer Science Balgrist University Hospital University of Zurich Lengghalde 5 Zurich Zurich8008 Switzerland Department of Orthopaedics Balgrist University Hospital University of Zurich Forchstrasse 340 Zurich Zurich8008 Switzerland Computer Vision and Geometry Group ETH Zurich Ramistrasse 101 Zurich Zurich8092 Switzerland Institute of Computer Science School of Engineering Zurich University of Applied Sciences Obere Kirchgasse 2 Winterthur Zurich8401 Switzerland Institute of Data Analysis and Process Design School of Engineering Zurich University of Applied Sciences Technikumstrasse 81 Winterthur Zurich8400 Switzerland

Background: Total Hip Arthroplasty (THA) is a well-established and common orthopedic surgery. Due to the complexity involved in THA, orthopedic surgeons require rigorous training. However, the current gold standard, the tutor-guided and -evaluated apprenticeship model is time-consuming, costly, and poses risks to patients. There is a pressing need for additional training resources to enhance the efficiency and safety of the training process. In this work, we present a novel Augmented Reality (AR)-based simulator designed for THA that helps enable a new self-paced training and learning paradigm without the need for ***: The simulator reduces the need for instructors by integrating an AR guidance module and an automated performance evaluation module. Three types of AR guidance were developed: Overlay, Virtual Twin, and Sectional Views. A feasibility study was conducted with five resident surgeons and two senior surgeons to compare these guidance methods quantitatively and qualitatively. The automated performance evaluation module was assessed against manual performance evaluation using Bland-Altman analysis with limits of agreement (LoA) and Mann-Whitney U ***: The quantitative feasibility results indicate the efficacy of the developed AR guidance, characterized by mean transitional and rotational deviation errors below 3 mm and 3 degrees. Based on the qualitative results, we provide recommendations for efficient AR guidance designs. The Bland-Altman analysis results (0.22 ± 1.32 mm with LoA -2.37 to 2.81 mm for distance deviation, 0.94 ± 2.41 degrees with LoA -3.78 to 5.66 degrees for yaw deviation, -0.34 ± 1.30 degrees with LoA -2.90 to 2.22 degrees for pitch deviation) and p-values of Mann-Whitney U tests (0.64 for distance deviation, 0.12 for yaw deviation, 0.11 for pitch deviation) indicate no statistically significant differences between the automated and manual performance evaluation at a significance level of ***: This wor

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Localization of Dummy data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach

arXiv

引用

arXiv 2024年

作者： Qu, Zhaoyang Dong, Yunchang Li, Yang Song, Siqi Jiang, Tao Li, Min Wang, Qiming Wang, Lei Bo, Xiaoyong Zang, Jiye Xu, Qi School of Electrical Engineering Northeast Electric Power University Jilin China Jilin Electric Power Research Institute of State Grid Changchun China Northeast Electric Power Design and Institute Co. Ltd. China Power Engineering Consulting Group China School of Computer Northeast Electric Power University Jilin China Jilin Engineering Technology Research Center of Intelligent Electric Power Big Data Processing Jilin China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong

The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing research predominantly focuses on various machine learning techniques, often analyzing the temporal data sequences post-attack or relying solely on Euclidean spatial characteristics. Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization. To address this issue, this study takes a comprehensive approach. Initially, it examines the underlying principles of these new DDIAs on power systems. Here, an intricate mathematical model of the DDIA is designed, accounting for incomplete topological knowledge and alternating current (AC) state estimation from an attacker's perspective. This model aims to mitigate the vulnerabilities associated with direct current (DC) flow-based attack data generation methods that can be readily detected. Subsequently, by integrating a priori knowledge of grid topology and considering the temporal correlations within measurement data and the topology-dependent attributes of the power grid, this study introduces temporal and spatial attention matrices. These matrices adaptively capture the spatio-temporal correlations within the attacks. Leveraging gated stacked causal convolution and graph wavelet sparse convolution, the study jointly extracts spatio-temporal DDIA features. This methodology significantly enhances the dynamic correlation mining capability while improving computational efficiency in the neighborhood. Finally, the research proposes a DDIA localization method based on spatio-temporal graph

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications

arXiv

引用

arXiv 2023年

作者： Lin, Jiatai Han, Guoqiang Xu, Xuemiao Liang, Changhong Wong, Tien-Tsin Chen, C.L. Philip Liu, Zaiyi Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Southern Medical University Guangzhou510080 China School of Computer Science and Engineering South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weighted aggregation of the feature maps by activating the high class-relevance ones. Current CAM methods achieve it relying on the training outcomes, such as predicted scores (forward information), gradients (backward information), etc. However, when with small-scale data, unstable training may lead to less effective model outcomes and generate unreliable weights, finally resulting in incorrect activation and noisy CAM seeds. In this paper, we propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. Since broad learning system (BLS) is independent to the model learning, BroadCAM can avoid the weights being affected by the unreliable model outcomes when with small-scale data. By evaluating BroadCAM on VOC2012 (natural images) and BCSS-WSSS (medical images) for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance than existing CAM methods with small-scale data (less than 5%) in different CNN architectures. It also achieves SOTA performance with large-scale training data. Extensive qualitative comparisons are conducted to demonstrate how BroadCAM activates the high class-relevance feature maps and generates reliable CAMs when with small-scale training data. © 2023, CC BY.

关键词： Learning systems

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：