检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Yang Chen, Chen Wang, Can King, Xulin Liu, Mengyuan College of Computer Science Sichuan University China Center for Research in Computer Vision University of Central Florida United States Laboratory on Multimedia Information Processing The Department of Computer Science Kiel University Hangzhou Linxrobot Company China Hangzhou GOTHEN Technology Co. Ltd China Key Laboratory of Machine Perception Shenzhen Graduate School Peking University China

Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling between the encoder and decoder is incomplete, which limits the encoder’s representation learning ability. Secondly, downstream tasks solely utilize the encoder, failing to fully leverage the knowledge acquired through the encoder-decoder architecture in the pre-text task. In this paper, we propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. The proposed method decouples functions between the decoder and the encoder by introducing a mask regressor, which predicts the masked patch representation from the visible patch representation encoded by the encoder and the decoder reconstructs the target from the predicted masked patch representation. By doing so, we minimize the impact of decoder updates on the representation space of the encoder. Moreover, we introduce an alignment constraint to ensure that the representations for masked patches, predicted from the encoded representations of visible patches, are aligned with the masked patch presentations computed from the encoder. To make full use of the knowledge learned in the pre-training stage, we design a new finetune mode for the proposed Point-RAE. Extensive experiments demonstrate that our approach is efficient during pre-training and generalizes well on various downstream tasks. Specifically, our pretrained models achieve a high accuracy of 90.28% on the ScanObjectNN hardest split and 94.1% accuracy on ModelNet40, surpassing all the other self-supervised learning methods. Our code and pretrained model are public available at: https://***/liuyyy111/ Point-RAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Determining Mice Sex from Chest X-rays using Deep learning

Determining Mice Sex from Chest X-rays using Deep Learning

引用

International Conference on Cyberspace (CYBER)

作者： Abiodun Ajiboye Kola Babalola Institute of Computer Vision and Machine Learning Lagos Nigeria European Molecular Biology Laboratory European Bioinformatics Institute Cambridgshire UK

ISBN: (纸本)9781665444095;9781665444101

This Following on from work by Babalola et al. It is shown that the sex of mice can be determined from x-ray images of the chest region alone using convolutional neural networks. The anatomical differences that may be responsible for this is further sinvestigated, as it may be useful in determining phenotype changes caused by knocking out genes - hence in understanding genotype-phenotype effects. Our results indicate that the cervical vertebrae may play an important role in the ability of our convolutional neural network to classify the sex of mice correctly using only x-rays of the chest region.

关键词： Deep learning Conferences Mice Convolutional neural networks X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

FedMLC: White-box Model Watermarking for Copyright Protection in Federated learning for IoT Environment

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Weitong Zhang, Wei Wu, Di Keskinarkaus, Anja Seppanen, Tapio Zhang, Jiale Gao, Longxiang Luan, Tom H. Yangzhou University School of Information Engineering Yangzhou225009 China ToowoombaQLD4350 Australia University of Oulu Physiological Signal Analysis Team Center for Machine Vision and Signal Analysis Oulu90014 Finland University of Southern Queensland SoMPC ToowoombaQLD4350 Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

With the widespread application of the Internet of Things (IoT), data processing has gradually migrated to edge devices that are closer to the data source. This shift has significantly improved the ability of real-time data analysis while effectively reducing bandwidth requirements and latency. Furthermore, Federated learning (FL) has been introduced as a decentralized training method to achieve collaborative training of multiple devices while ensuring local data privacy. However, malicious clients in FL may theft trained models for unauthorized use, which causes model misuse or copyright challenges. To address these issues, this paper proposes FedMLC (Malicious client detection, Leakage tracing, and Copyright verification), a server-side white-box watermarking scheme. FedMLC utilizes the embedded watermark at different stages to achieve both traceability and copyright verification, simplifying the watermarking process. Additionally, the watermarking can also detect malicious clients in FL. Specifically, FedMLC uses the regularization term to guide the parameter signs of the normalization layer to be consistent with the watermark sign, thereby achieving watermark embedding. Experimental results show that our FL model watermarking scheme excels in malicious client detection, leakage tracing, and copyright verification, with minimal impact on model performance, able to resist various attacks such as fine-tuning, pruning, and quantization. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Group-specific discriminant analysis reveals statistically validated sex differences in lateralization of brain functional network

arXiv

引用

arXiv 2024年

作者： Zhou, Shuo Luo, Junhao Jiang, Yaya Wang, Haolin Lu, Haiping Gong, Gaolang Department of Computer Science University of Sheffield Sheffield United Kingdom Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom State Key Laboratory of Cognitive Neuroscience and Learning IDG/McGovern Institute for Brain Research Beijing Normal University Beijing China Beijing Key Laboratory of Brain Imaging and Connectomics Beijing Normal University Beijing China Chinese Institute for Brain Research Beijing China

Lateralization is a fundamental feature of the human brain, where sex differences have been observed. Conventional studies in neuroscience on sex-specific lateralization are typically conducted on univariate statistical comparisons between male and female groups. However, these analyses often lack effective validation of group specificity. Here, we formulate modeling sex differences in lateralization of functional networks as a dual-classification problem, consisting of first-order classification for left vs. right functional networks and second-order classification for male vs. female models. To capture sex-specific patterns, we develop the Group-Specific Discriminant Analysis (GSDA) for first-order classification. The evaluation on two public neuroimaging datasets demonstrates the efficacy of GSDA in learning sex-specific models from functional networks, achieving a significant improvement in group specificity over baseline methods. The major sex differences are in the strength of lateralization and the interactions within and between lobes. The GSDA-based method is generic in nature and can be adapted to other group-specific analyses such as handedness-specific or disease-specific analyses. © 2024, CC BY-NC-SA.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Collaborative visual navigation

arXiv

引用

arXiv 2021年

作者： Wang, Haiyang Wang, Wenguan Zhu, Xizhou Dai, Jifeng Wang, Liwei Key Laboratory of Machine Perception MOE Peking University SenseTime Research Computer Vision Lab ETH Zurich

As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques. However, previous MARL methods largely focused on grid-world like or game environments;MAS in visually-rich environments has remained less explored. To narrow this gap and emphasize the crucial role of perception in MAS, we propose a large-scale 3D dataset, CollaVN, for multi-agent visual navigation (MAVN). In CollaVN, multiple agents are entailed to cooperatively navigate across photo-realistic environments to reach target locations. Diverse MAVN variants are explored to make our problem more general. Moreover, a memory-augmented communication framework is proposed. Each agent is equipped with a private, external memory to persistently store communication information. This allows agents to make better use of their past communication information, enabling more efficient collaboration and robust long-term planning. In our experiments, several baselines and evaluation metrics are designed. We also empirically verify the efficacy of our proposed MARL approach across different MAVN task settings. © 2021, CC BY.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Super-resolution on Low-resolution Micro-expression Recognition

arXiv

引用

arXiv 2023年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying The School of Computer Science and Engineering Macau University of Science and Technology China The Key Laboratory of Child Development and Learning Science Ministry of Education Southeast University Nanjing210096 China School of Computer Engineering Nanjing Institute of Technology Jiangsu China The School of Biological Science and Medical Engineering Southeast University Jiangsu Nanjing210096 China The School of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang China The Center for Machine Vision and Signal Analysis University of Oulu Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution techniques for enhancing the quality of LR images and videos, few study has focused on investigate super-resolution for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of super-resolution-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both super-resolution (SR) and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 13 SOTA SR techniques, thereby addressing the problem of super-resolution in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Classification of WeChat Mini-Apps

Convolutional Neural Network Based Classification of WeChat ...

引用

IEEE International Conference on Communications (ICC)

作者： Yihao Jin Xuanyu Liu Xiao Fu Bin Luo Xiaojiang Du Mohsen Guizani State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE

In recent years, a novel mobile computing paradigm has been evolving rapidly, with a host app allowing users to install and run mini-apps inside the app itself. However, the current classification mechanism of mini-apps is blurry and coarse-grained, making users unable to clearly understand mini-app functions, which can result in a series of privacy issues. In this study, an automatic convolutional neural network (CNN)-based classification approach is proposed for Wechatmini-apps. The proposed method integrates the static and dynamic features of WeChat mini-apps to achieve precise classification. Our approach was evaluated in a real-world testbed and the results showed that it can effectively classify Wechatmini-apps into proper categories, helping users better understand the functions of WeChat mini-apps while reducing user privacy violations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis

arXiv

引用

arXiv 2023年

作者： Zheng, Kaizhong Yu, Shujian Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Machine Learning Group UiT - Arctic University of Norway Tromsø Norway

There is a recent trend to leverage the power of graph neural networks (GNNs) for brain-network based psychiatric diagnosis, which, in turn, also motivates an urgent need for psychiatrists to fully understand the decision behavior of the used GNNs. However, most of the existing GNN explainers are either post-hoc in which another interpretive model needs to be created to explain a well-trained GNN, or do not consider the causal relationship between the extracted explanation and the decision, such that the explanation itself contains spurious correlations and suffers from weak faithfulness. In this work, we propose a granger causality-inspired graph neural network (CI-GNN), a built-in interpretable model that is able to identify the most influential subgraph (i.e., functional connectivity within brain regions) that is causally related to the decision (e.g., major depressive disorder patients or healthy controls), without the training of an auxillary interpretive network. CI-GNN learns disentangled subgraph-level representations α and β that encode, respectively, the causal and non-causal aspects of original graph under a graph variational autoencoder framework, regularized by a conditional mutual information (CMI) constraint. We theoretically justify the validity of the CMI regulation in capturing the causal relationship. We also empirically evaluate the performance of CI-GNN against three baseline GNNs and four state-of-the-art GNN explainers on synthetic data and three large-scale brain disease datasets. We observe that CI-GNN achieves the best performance in a wide range of metrics and provides more reliable and concise explanations which have clinical evidence. The source code and implementation details of CI-GNN are freely available at GitHub repository (https://***/ZKZ-Brain/CI-GNN/). Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

The Spatial-Temporal Evolution and Influencing Factors of Public Attention to 5G: Empirical Analysis Based on Baidu Index from 2011 to 2021

引用

Mathematical Problems in Engineering 2023年第1期2023卷

作者： Liu, Pan Wang, Guanyu Liu, Kai Li, Junke Chen, Yanlin School of Information Engineering Suqian University Jiangsu Suqian223800 China School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Machine Learning and Unstructured Data Processing of Qiannan Guizhou Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000 China

The development of 5G (fifth-generation wireless systems) determines the future direction of technology and economy and has received extensive public attention. Studying the changing rules of public attention to 5G can provide an important guiding significance for the sustainable development of 5G. This paper takes Baidu Index as the measurement index of 5G public attention and analyzes the spatial and temporal evolution characteristics and influencing factors of public attention to 5G from 2011 to 2021 by using the elasticity coefficient, Gini coefficient, geographical concentration index, and panel data model. The results of the study show the following. (1) The public concern to 5G is generally on the rise, but the heat has declined in the past two years. (2) The public’s 5G attention shows a seasonal effect, with the highest attention in March and June. (3) The spatial difference of 5G public attention is obvious. The eastern region has a high degree of attention, the internal differences between the eastern and western regions are obvious, and the central region is relatively balanced. (4) The factors such as local economic level, education level, Internet development, and media attention have significantly affected the public focus on 5G. Also, some suggestions are made for the sustainable development of 5G and the planning of 6G (sixth-generation wireless systems). Copyright © 2023 Pan Liu et al.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Exploiting Completeness and Uncertainty of Pseudo Labels for...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Chen Zhang Guorong Li Yuankai Qi Shuhui Wang Laiyun Qing Qingming Huang Ming-Hsuan Yang State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Australian Institute for Machine Learning The University of Adelaide Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS University of California Merced

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

关键词：

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：