检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wenke Huang Mang Ye Zekun Shi He Li Bo Du National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Federated learning shows a bright promise as a privacy-preserving collaborative learning technique. However, prevalent solutions mainly focus on all private data sampled from the same domain. An important challenge is that when distributed data are derived from diverse domains. The private model presents degenerative performance on other domains (with domain shift). Therefore, we expect that the global model optimized after the federated learning process stably provides generalizability performance on multiple domains. In this paper, we propose Federated Proto-types Learning (FPL) for federated learning under domain shift. The core idea is to construct cluster prototypes and unbiased prototypes, providing fruitful domain knowledge and a fair convergent target. On the one hand, we pull the sample embedding closer to cluster prototypes belonging to the same semantics than cluster prototypes from distinct classes. On the other hand, we introduce consistency regularization to align the local instance with the respective unbiased prototype. Empirical results on Digits and Office Caltech tasks demonstrate the effectiveness of the proposed solution and the efficiency of crucial modules.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic State Estimation-Based Protection for Induction Motor Loads

Dynamic State Estimation-Based Protection for Induction Moto...

引用

2022 North American Power Symposium, NAPS 2022

作者： Barnes, Arthur K. Basu, Sarbajit Mate, Adam Advanced Network Science Initiative at Los Alamos National Laboratory Los AlamosNM87545 United States New Mexico State University Klipsch School of Electrical and Computer Engineering Las CrucesNM88003 United States

ISBN: (纸本)9781665499217

Ensuring protective device coordination is critical to maintain the resilience and improve the reliability of large microgrids. Inverter-interfaced generation, however, poses significant challenges when designing protection systems. Traditional time-overcurrent protective devices are unsuitable on account of the lack of fault current. Present industry practice is to force all inverters to shut down during faults, which prevents large microgrids from operating in a resilient and reliable manner. Dynamic state estimation (DSE) has been proposed for line protection, and more recently for the protection of load buses or downstream radial portions of microgrids. However, only passive loads with series resistive-inductive loads have been tested with DSE, even though the behavior of dynamic loads - such as induction motors or power electronics - may differ significantly during faults. This paper considers the case of applying DSE to protecting a load bus serving a three-phase induction motor. © 2022 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

arXiv

引用

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Cross-Modal Implicit Relation Reasoning and Aligning for Tex...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Ding Jiang Mang Ye National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Algorithm Contest of Calibration-free Motor Imagery BCI in the BCI Controlled Robot Contest in World Robot Contest 2021:A survey

引用

Brain Science Advances 2022年第2期8卷 127-141页

作者： Jing Luo Qi Mao Yaojie Wang Zhenghao Shi Xinhong Hei Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and EngineeringXi’an University of TechnologyXi’an 710054ShaanxiChina

Objective:From September 10 to 13,2021,the finals of the BCI Controlled Robot Contest in World Robot Contest 2021 were held in Beijing,*** teams participated in the Algorithm Contest of Calibration-free Motor Imagery *** participants employed both traditional electroencephalograph(EEG)analysis methods and deep learning-based methods in the *** this paper,we reviewed the algorithms utilized by the participants,extracted the trends and highlighted interesting approaches from these methods to inform future contests and research ***:First,we analyzed the algorithms in separate steps,including EEG channel and signal segment setup,prepossessing technology,and classification ***,we emphasized the highlights of each ***,we compared the competition algorithm with the SOTA ***:The algorithm employed in the finals performed better than that of the SOTA *** the final stage of the contest,four of the top five teams used convolutional neural network models,suggesting that with the rapid development of deep learning,convolutional neural network-based models have been the most popular methods in the field of motor imagery BCI.

关键词： brain-computer interface motor imagery con-volutional neural network World Robot Contest

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

arXiv

引用

arXiv 2023年

作者： Jiang, Ding Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Dictionary Learning network for Sparse View Ct Reconstruction with a Group Sparse Prior

SSRN

引用

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A survey of IPv6 address scanning techniques 2

A survey of IPv6 address scanning techniques

引用

2nd International Conference on Frontiers of Applied Optics and computer engineering, AOCE 2025

作者： Cheng, Xingqi Jing, Shan Jiao, Liang Zhao, Chuan Yang, Hongjuan School of Information Science and Engineering University of Jinan Jinan China National Computer Network Emergency Response Technical Team Coordination Center of China Shandong Branch China Quan Cheng Laboratory Jinan China

ISBN: (纸本)9781510689404

Current scanning techniques are capable of rapidly covering the entire IPv4 address space. However, for the almost endless address space of IPv6, it is impossible to use current scanning techniques to scan for hundreds of millions of years. In recent years, numerous researchers have developed various heuristic based IPv6 address scanning methods to address this issue. These methods effectively reduce the scope of addresses that need to be scanned by utilizing collected initial IPv6 addresses as starting points, and generating a list of potentially active IPv6 addresses to focus on for scanning. This paper systematically categorizes, organizes, and reviews these seed-address-based techniques, and it thoroughly examines the strengths and weaknesses of each algorithm. This paper selects addresses from the latest publicly available dataset, Hitlist, to serve as seed addresses. Through experiments, a comprehensive comparison of 11 address scanning techniques is conducted, and a tool for the automated evaluation of address scanning techniques is developed. © The Authors.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

A Data Security Protection Method for Deep Neural network Model Based on Mobility and Sharing 1

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Zhao, Xinjian Li, Qianmu Wang, Qi Chen, Shi Li, Tengfei Li, Nianzhe State Grid Jiangsu Information and Telecommunication Company Jiangsu Nanjing210024 China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China State Grid Smart Grid Research Institute Co. Ltd. Jiangsu Nanjing210003 China State Grid Key Laboratory of Information and Network Security Jiangsu Nanjing210003 China

ISBN: (数字)9789819998937

ISBN: (纸本)9789819998920

With the rapid development of digital economy, numerous business scenarios, such as smart grid, energy network, intelligent transportation, etc., require the design and distribution of deep neural network (DNN) models, which typically use large amounts of data and computing resources for training. As a result, DNN models are now considered important assets, but at great risk of being stolen and distributed illegally. In response to the new risks and challenges brought by frequent data flow and sharing, watermarks have been introduced to protect the ownership of DNN models. Watermarks can be extracted in a relatively simple manner to declare ownership of a model. However, watermarks are vulnerable to attacks. In this work, we propose a novel label-based black-box watermark model protection algorithm. Inspired by new labels, we design a method to embed watermarks by adding new labels in the model, and to prevent watermarks from being forged, we use encryption algorithms to generate key samples. We conduct experiments on the VGG19 model using the CIFAR-10 dataset. Experimental results show that the method is robust to fine-tuning attacks, pruning attacks. Furthermore, our method does not affect the performance of deep neural network models. This method helps to solve scenarios such as "internal data circulation, external data sharing and multi-party data collaboration". © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

TFLAG: Towards Practical APT Detection via Deviation-Aware Learning on Temporal Provenance Graph

arXiv

引用

arXiv 2025年

作者： Jiang, Wenhan Chai, Tingting Liu, Hongri Wang, Kai Zhang, Hongke School of Computer Science and Technology Harbin Institute of Technology Weihai China Shandong Key Laboratory of Industrial Network Security China School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China

Advanced Persistent Threat (APT) have grown increasingly complex and concealed, posing formidable challenges to existing Intrusion Detection Systems in identifying and mitigating these attacks. Recent studies have incorporated graph learning techniques to extract detailed information from provenance graphs, enabling the detection of attacks with greater granularity. Nevertheless, existing studies have largely overlooked the continuous yet subtle temporal variations in the structure of provenance graphs, which may correspond to surreptitious perturbation anomalies in ongoing APT attacks. Therefore, we introduce TFLAG, an advanced anomaly detection framework that for the first time integrates the structural dynamic extraction capabilities of temporal graph model with the anomaly delineation abilities of deviation networks to pinpoint covert attack activities in provenance graphs. This self-supervised integration framework leverages the graph model to extract neighbor interaction data under continuous temporal changes from historical benign behaviors within provenance graphs, while simultaneously utilizing deviation networks to accurately distinguish authentic attack activities from false positive deviations due to unexpected subtle perturbations. The experimental results indicate that, through a comprehensive design that utilizes both attribute and temporal information, it can accurately identify the time windows associated with APT attack behaviors without prior knowledge (e.g., labeled data samples), demonstrating superior accuracy compared to current state-of-the-art methods in differentiating between attack events and system false positive events. © 2025, CC BY.

关键词： Contrastive Learning

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：