检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Dynamic Prefix-Tuning for Generative Template-based Event Extraction

arXiv

引用

arXiv 2022年

作者： Liu, Xiao Huang, Heyan Shi, Ge Wang, Bo School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Key Laboratory of Intelligent Information Processing and Information Security Ministry of Industry and Information Technology China Southeast Academy of Information Technology Beijing Institute of Technology China Faculty of Information Technology Beijing University of Technology China

We consider event extraction in a generative manner with template-based conditional generation. Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information. In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DYNPREF) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context. Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model ONEIE on ACE 2005 and achieves the best performances on ERE. Additionally, our model is proven to be portable to new types of events effectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Distortion-Disentangled Contrastive Learning

Distortion-Disentangled Contrastive Learning

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Jinfeng Wang Sifan Song Jionglong Su S. Kevin Zhou School of AIAC Xi’an Jiaotong-Liverpool University Suzhou China School of BME & Suzhou Institute for Advanced Research Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) University of Science and Technology of China Suzhou China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

Self-supervised learning is well known for its remarkable performance in representation learning and various downstream computer vision tasks. Recently, Positive-pair-Only Contrastive Learning (POCL) has achieved reliable performance without the need to construct positive-negative training sets. It reduces memory requirements by lessening the dependency on the batch size. The POCL method typically uses a single objective function to extract the distortion invariant representation (DIR) which describes the proximity of positive-pair representations affected by different distortions. This objective function implicitly enables the model to filter out or ignore the distortion variant representation (DVR) affected by different distortions. However, some recent studies have shown that proper use of DVR in contrastive can optimize the performance of models in some downstream domain-specific tasks. In addition, these POCL methods have been observed to be sensitive to augmentation strategies. To address these limitations, we propose a novel POCL framework named Distortion-Disentangled Contrastive Learning (DDCL) and a Distortion-Disentangled Loss (DDL). Our approach is the first to explicitly and adaptively disentangle and exploit the DVR inside the model and feature stream to improve the representation utilization efficiency, robustness and representation ability. Experiments demonstrate our framework’s superiority to Barlow Twins and Simsiam in terms of convergence, representation quality (including transferability and generalization), and robustness on several datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-Causal Learning for Single Domain Generalization

Meta-Causal Learning for Single Domain Generalization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jin Chen Zhi Gao Xinxiao Wu Jiebo Luo Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Computer Science University of Rochester Rochester NY USA

Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. In this paper, we propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation. Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training. We use the meta-knowledge to analyze the shift between the target and source domains during testing. Specifically, we perform multiple transformations on source data to generate the auxiliary domain, perform counterfactual inference to learn to discover the causal factors of the shift between the auxiliary and source domains, and incorporate the inferred causality into factor-aware domain alignments. Extensive experiments on several benchmarks of image classification show the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey

arXiv

引用

arXiv 2024年

作者： Qi, Yayun Li, Hongxi Song, Yiqi Wu, Xinxiao Luo, Jiebo Beijing Laboratory of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Beijing100081 China Guangdong Provincial Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Shenzhen518172 China Department of Computer Science University of Rochester RochesterNY14627 United States

The exploration of various vision-language tasks, such as visual captioning, visual question answering, and visual commonsense reasoning, is an important area in artificial intelligence and continuously attracts the research community’s attention. Despite the improvements in overall performance, classic challenges still exist in vision-language tasks and hinder the development of this area. In recent years, the rise of pre-trained models is driving the research on vision-language tasks. Thanks to the massive scale of training data and model parameters, pretrained models have exhibited excellent performance in numerous downstream tasks. Inspired by the powerful capabilities of pretrained models, new paradigms have emerged to solve the classic challenges. Such methods have become mainstream in current research with increasing attention and rapid advances. In this paper, we present a comprehensive overview of how vision-language tasks benefit from pre-trained models. First, we review several main challenges in vision-language tasks and discuss the limitations of previous solutions before the era of pre-training. Next, we summarize the recent advances in incorporating pretrained models to address the challenges in vision-language tasks. Finally, we analyze the potential risks associated with the inherent limitations of pre-trained models and discuss possible solutions, attempting to provide future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Research on Proofreading Method of Semantic Collocation Error in Chinese 7th

Research on Proofreading Method of Semantic Collocation Erro...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Zhang, Rui Zhang, Yangsen Huang, Gaijuan Chen, Ruoyu Institute of Intelligent Information Processing Beijing Information Science and Technology University Beijing100192 China Beijing Laboratory of National Economic Security Early-Warning Engineering Beijing100044 China

ISBN: (纸本)9783030786144

With the rapid development of network technology and the popularization of electronic documents, Chinese text automatic proofreading technology has attracted increasing attention. Automatic proofreading of semantic errors in Chinese text is a key and difficult point in the field of Chinese information processing. Aiming at this problem, we propose a semantic error proofreading method that contains dependency parsing and statistical theory, and construct a two-layer semantic knowledge base to assist error detection and error correction. The two-layer semantic knowledge base includes (1) knowledge base of word collocations containing structured information of sentences extracted from a large-scale corpus;(2) knowledge base of sememe collocations obtained by sememe mapping through HowNet. On this basis, cubic association ratio and degree of polymerization are introduced to evaluate the proofreading results to reduce false positives and improve the accuracy of error correction opinions. The experiment result shows that our method will be of great use for the construction of semantic proofreading knowledge base and semantic error automatic proofreading methods. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Malicious URL Identification and Analysis for Network Security 7

Research on Malicious URL Identification and Analysis for Ne...

引用

7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021

作者： Huang, Zhuofan Zhang, Yangsen Duan, Ruixue Wang, Renjie Beijing Information Science and Technology University Institute of Intelligent Information Processing Beijing100101 China Beijing Laboratory of National Economic Security Early Warning Engineering Beijing100044 China

ISBN: (纸本)9781665405829

With the rapid development of the Internet, the emergence of various malicious URLs seriously endangers the national network information security and user information security. Therefore, it is of great theoretical significance and practical value for network security to accurately identify and deal with malicious URLs. This paper proposes a research method of character level feature extraction and recognition of malicious URLs based on CNN + BiLSTM + CNN model. Based on the massive URL data sets, the parameter distribution characteristics of malicious URLs are analyzed, and the skip gram model is introduced to unsupervised train the preprocessed data sets, so as to embed the characters of URLs. Then the CNN + BiLSTM + CNN model is introduced to extract and optimize the local and temporal features of malicious URLs. The experimental results show that on the same data set, the malicious URL recognition method based on CNN + BiLSTM + CNN model has better recognition effect and higher accuracy than the traditional BiLSTM based algorithm and CNN based algorithm. The F1 value is increased to 98.14%, and the average iteration time is greatly reduced. It shows that the research method proposed in this paper has good applicability in the field of malicious URL identification for network security. © 2021 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Zombie Hosts Identification Based on DNS Log 7

Zombie Hosts Identification Based on DNS Log

引用

7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021

作者： Wang, Renjie Zhang, Yangsen Duan, Ruixue Huang, Zhuofan Beijing Information Science and Technology University Institute of Intelligent Information Processing Beijing100101 China Beijing Laboratory of National Economic Security Early-warning Engineering Beijing100044 China

ISBN: (纸本)9781665405829

Although the academia has done a lot of research on DNS abnormal behavior, whether from the perspective of traffic or irregular domain name recognition, the mechanism behind DNS is ignored in the pre-processing of DNS logs and other data. In addition, most studies focus on traffic anomaly detection and unconventional domain name recognition, and lack of systematic research on the combination of the two, so the proposed algorithm has no practical application. This paper proposes a clustering method based on DNS client IP address traffic characteristics, which divides DNS logs into five access modes. Then, a DNS log preprocessing algorithm is designed to preprocess the logs that may exist in zombie hosts. Finally, a two-layer GRU network detection algorithm based on domain name text features is proposed. Experimental results show that this method can effectively identify zombie hosts in DNS logs. © 2021 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

NetGO 3.0:Protein Language Model Improves Large-scale Functional Annotations

引用

Genomics, Proteomics & Bioinformatics 2023年第2期21卷 349-358页

作者： Shaojun Wang Ronghui You Yunjia Liu Yi Xiong Shanfeng Zhu Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China School of Life Sciences Fudan UniversityShanghai 200433China Department of Bioinformatics and Biostatistics Shanghai Jiao Tong UniversityShanghai 200240China Shanghai Artificial Intelligence Laboratory Shanghai 200232China Shanghai Qi Zhi Institute Shanghai 200030China MOEKey Laboratoryof Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai 200433China Shanghai Key Laboratory of Intelligent Information Processing and Shanghai Institute of Artificial Intelligence Algorithm Fudan UniversityShanghai 200433China Zhangjiang Fudan International Innovation Center Shanghai 200433China

As one of the state-of-the-art automated function prediction(AFP)methods,NetGO 2.0 integrates multi-source information to improve the ***,it mainly utilizes the proteins with experimentally supported functional annotations without leveraging valuable information from a vast number of unannotated ***,protein language models have been proposed to learn informative representations[e.g.,Evolutionary Scale Modeling(ESM)-1b embedding] from protein sequences based on ***,we represented each protein by ESM-1b and used logistic regression(LR)to train a new model,LR-ESM,for *** experimental results showed that LR-ESM achieved comparable performance with the best-performing component of NetGO ***,by incorporating LR-ESM into NetGO 2.0,we developed NetGO 3.0 to improve the performance of AFP extensively.

关键词： Protein function prediction Web service Protein language model Learning to rank Large-scale multi-label learning

来源：评论

学校读者我要写书评

暂无评论

FedCross: Intertemporal Federated Learning Under Evolutionary Games

arXiv

引用

arXiv 2024年

作者： Lu, Jianfeng Zhang, Ying Jia, Riheng Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China School of Computer Science and Technology Zhejiang Normal University China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally. However, dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation severely hinder model updates to the cloud server. Although previous studies have typically addressed user mobility issue through task reassignment or predictive modeling, frequent migrations may result in high communication overhead. Addressing this challenge involves not only dealing with resource constraints, but also finding ways to mitigate the challenges posed by user migrations. We therefore propose an intertemporal incentive framework, FedCross, which ensures the continuity of FL tasks by migrating interrupted training tasks to feasible mobile devices. Specifically, FedCross comprises two distinct stages. In Stage 1, we address the task allocation problem across regions under resource constraints by employing a multi-objective migration algorithm to quantify the optimal task receivers. Moreover, we adopt evolutionary game theory to capture the dynamic decision-making of users, forecasting the evolution of user proportions across different regions to mitigate frequent migrations. In Stage 2, we utilize a procurement auction mechanism to allocate rewards among base stations, ensuring that those providing high-quality models receive optimal compensation. This approach incentivizes sustained user participation, thereby ensuring the overall feasibility of FedCross. Finally, experimental results validate the theoretical soundness of FedCross and demonstrate its significant reduction in communication overhead. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated 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：