检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shen, Yuchen Zhang, Dong Zhang, Zhao Fu, Liyong Ye, Qiaolin College of Information Science and Technology & Artificial Intelligence Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China College of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Institute of Forest Resource Information Techniques Chinese Academy of Forestry Beijing100091 China

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In contrast, weakly-supervised instance segmentation methods, such as those using image-level class labels or point labels, often struggle to satisfy the accuracy and recall requirements of practical scenarios. In this paper, we propose a novel paradigm called Synthetic Instance Segmentation (SISeg). SISeg achieves instance segmentation results by leveraging image masks generated by existing semantic segmentation models, and it is highly efficient as we do not require additional training for semantic segmentation or the use of instance-level image annotations. In other words, the proposed model does not need extra manpower or higher computational expenses. Specifically, we first obtain a semantic segmentation mask of the input image via an existent semantic segmentation model. Then, we calculate a displacement field vector for each pixel based on the segmentation mask, which can indicate representations belonging to the same class but different instances, i.e., obtaining the instance-level object information. Finally, the instance segmentation results are refined by a learnable category-agnostic object boundary branch. Extensive experimental results on two challenging datasets highlight the effectiveness of SISeg in achieving competitive results when compared to state-of-the-art methods, especially fully-supervised methods. The code will be released at: SISeg Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

arXiv

引用

arXiv 2023年

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the Anomaly Overfitting and Homophily Trap problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate Anomaly Overfitting. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An empirical examination of balancing strategy for counterfactual estimation on time series 24

An empirical examination of balancing strategy for counterfa...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Qiang Huang Chuizheng Meng Defu Cao Biwei Huang Yi Chang Yan Liu School of Artificial Intelligence and International Center of Future Science Jilin University Changchun Jilin China Department of Computer Science University of Southern California California Los Angeles Halicioğlu Data Science Institute University of California San Diego San Diego California School of Artificial Intelligence and International Center of Future Science Jilin University Changchun Jilin China and Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOE Changchun Jilin China

Counterfactual estimation from observations represents a critical endeavor in numerous application fields, such as healthcare and finance, with the primary challenge being the mitigation of treatment bias. The balancing strategy aimed at reducing covariate disparities between different treatment groups serves as a universal solution. However, when it comes to the time series data, the effectiveness of balancing strategies remains an open question, with a thorough analysis of the robustness and applicability of balancing strategies still lacking. This paper revisits counterfactual estimation in the temporal setting and provides a brief overview of recent advancements in balancing strategies. More importantly, we conduct a critical empirical examination for the effectiveness of the balancing strategies within the realm of temporal counterfactual estimation in various settings on multiple datasets. Our findings could be of significant interest to researchers and practitioners and call for a reexamination of the balancing strategy in time series settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal structure learning of nonlinear additive noise model based on streaming feature

Causal structure learning of nonlinear additive noise model ...

引用

IEEE International Conference on data Mining Workshops (ICDM Workshops)

作者： Jing Yang Gaojin Fan Anbo Shen Aiguo Wang Ministry of Education Key Laboratory of Knowledge Engineering With Big Data(Hefei University of Technology) School of Computer Science and Information Engineering Hefei University of Technology Hefei P. R. China School of Electronic and Information Engineering Foshan University China

ISBN: (纸本)9781665424288

The current streaming feature structure learning needs to be improved in the processing of nonlinear continuous data and the dynamic acquisition of causal structures. In this paper, we propose a causal structure learning algorithm, CANSF, based on the streaming feature of additive noise models. We have made three contributions. First, by using the information carried by the noise of nonlinear continuous data, we propose a real correlation identification method based on logarithmic likelihood, which can identify the real correlation and redundant features of target features, and dynamically select parent and child nodes for each feature. Second, based on regression analysis, a method to determine the causal direction is proposed, which can be used for dynamic orientation. Third, a learning method of causal structure based on streaming features is proposed, which can obtain the Causal structure diagram directly and dynamically.

关键词： Additive noise Learning systems Correlation Heuristic algorithms Conferences data models Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Design of Wireless data Center Network Structure Based on ExCCC-DCN 6th

Design of Wireless Data Center Network Structure Based on Ex...

引用

6th International Conference on data Science, ICDS 2019

作者： Jing, Yanhao Han, Zhijie Du, Xiaoyu Zhang, Qingfang School of Computer and Information Engineering Henan University KaifengHenan475004 China Institute of Data and Knowledge Engineering Henan University KaifengHenan475004 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Network NanjingJiangsu210003 China

ISBN: (纸本)9789811528095

A data center is a cluster of servers, which is typically an organic collection of tens of thousands of servers. The sheer number of servers determines how well its performance is related to how it is interconnected. Just like the topology of Ethernet determines its network capacity and communication characteristics, the network structure of the data center has a great impact on its performance and capacity. The research object ExCCC-DCN in this paper has excellent node capacity, and its construction cost and operating energy consumption are relatively low, which is very suitable for deploying large-scale data centers. However, ExCCC-DCN is deployed on a wired link, and a large number of wired links can make maintenance and upgrade of the data center more difficult. Therefore, this paper utilizes the advantages of high transmission rate, strong anti-interference and high security of 60 GHz millimeter wave to wirelessly transform ExCCC-DCN, making it more flexible in the case of maintaining communication efficiency. © Springer Nature Singapore Pte Ltd 2020.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A lightweight identity authentication scheme for UAV and road base stations 2020

A lightweight identity authentication scheme for UAV and roa...

引用

Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies

作者： Yinyin Li Xiaoyu Du Sufang Zhou International Joint Research Laboratory for Cooperative Vehicular Networks of Henan Kaifeng Henan University Kaifeng Henan School of Computer and Information Engineering Henan University Kaifeng Henan Institute of Data and Knowledge Engineering Henan University Kaifeng Henan

ISBN: (纸本)9781450387828

At present, unmanned aerial vehicles (UAVs) have been widely used in civilian fields (such as smart cities). However, the external environment of the UAV network is complex and computing resources are limited, so it is vulnerable to serious security threats, such as replay attacks, forgery attacks, man-in-the-middle attacks. Seriously, it will cause great damage to the work of the UAV in smart cities. Aiming at the problem of transmission instruction data leakage caused by malicious UAV in communication between road base stations and UAVs, this paper proposes a lightweight identity authentication scheme based on elliptic curve cryptography (ECC). The purpose is to ensure the identity authentication of the UAV and the road base station, to ensure that the mission instructions received by the UAV are authentic and reliable, and to ensure the privacy of the UAV's identity information. The algorithm mainly includes the system initialization phase, initializing the UAV and road base station, and the identity authentication phase. Compared with the traditional identity authentication method, this method has the characteristics of low computational cost, short key and high security, and is more suitable for UAV communication.

关键词： Identity authentication Elliptic curve cryptography (ECC) UAV and road base stations

来源：评论

学校读者我要写书评

暂无评论

Mapping Usability Heuristics to Medical Ethical Principles in Clinical Decision Support Design

引用

Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care 2021年第1期10卷 54 - 58页

作者： Tim Arnold Helen J.A. Fuller Scott D. Wood Human Factors Engineering Clinical Informatics and Data Management Office of Health Informatics Veterans Health Administration Washington DC USAUniversity of Michigan College of Pharmacy Ann Arbor USA Human Factors Engineering Clinical Informatics and Data Management Office of Health Informatics Veterans Health Administration Washington DC USA Knowledge Based Systems Clinical Informatics and Data Management Office of Health Informatics Veterans Health Administration Washington DC USA

Human factors professionals voice concerns about the slow and uneven adoption of human-centered design (HCD) principles in healthcare. With good intentions and best efforts, human factors work in healthcare continues, but to understand and to be understood we must share a language that speaks to one another. One way to facilitate this understanding is by bringing attention to how we talk about decision-making approaches in medical ethics and HCD. Both disciplines suggest efforts should be participatory, guided by a set of principles applied thoughtfully, with critical consideration to context and trade-offs. Considering the connections between usability heuristics for design and medical ethical principles may offer a bridge between disciplines and their associated dialects. In this paper, we provide three representations mapping ethical principles to design principles, including usability heuristics: a word tree visualization, narrative passages, and a table format. We believe this mapping demonstrates both that ethical design is inherently human-centric and that human-centered design is ethical design.

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：