检索结果-内蒙古大学图书馆

CLOE: Novelty Detection via Contrastive Learning with Outlier Exposure 1

16th International Conference on Intelligent Robotics and Applications, ICIRA 2023

作者： Liu, Tianyang Liang, Quan Yang, Hua Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9789819964987

ISBN: (纸本)9789819964970

Novelty detection (ND) methods seek to identify anomalies within a specific dataset. Although self-supervised representation learning is commonly used in such applications, inadequate training data may reduce the effectiveness of these methods. It is thus reasonable to use external data to improve these performances. Here, we propose a simple and effective network, CLOE, for image-based novelty detection. Our method includes a pretrained ViT model as a feature extractor and employs the contrastive learning technique to train the dataset with external data. We compare the performance of two types of extra training settings: (1) The augmented data of the original dataset. (2) The fake images obtained from generative models. The demonstrated approach achieves a new state-of-the-art performance in novelty detection, as evidenced by achieving an ROC-AUC of 99.72% on the CIFAR-10 dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

SADBA: Self-Adaptive Distributed Backdoor Attack Against Federated Learning 39

SADBA: Self-Adaptive Distributed Backdoor Attack Against Fed...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Feng, Jun Lai, Yuzhe Sun, Hong Ren, Bocheng Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Economics Wuhan Textile University China School of Computer Science and Technology Hainan University China

ISBN: (纸本)157735897X

Backdoor attacks in federated learning (FL) face challenges such as lower attack success rates and compromised main task accuracy (MA) compared to local training. Existing methods like distributed backdoor attack (DBA) mitigate these issues by modifying malicious clients’ updates and partitioning global triggers to enhance backdoor persistence and stealth. The recent full combination backdoor attack (FCBA) further improves backdoor efficiency with a full combination strategy. However, these methods are mainly applicable in small-scale FL. In large-scale FL, small trigger patterns weaken impact, and scaling them requires controlling exponentially more clients, which poses significant challenges, while simply reverting to DBA may decrease backdoor performance. To overcome these challenges, we propose the self-adaptive distributed backdoor attack (SADBA), which achieves similar performance to FCBA with a lower percentage of malicious clients (PMC). It also adapts more flexibly through an optimized model poisoning strategy and a self-adaptive data poisoning strategy. Experiments demonstrate SADBA outperforms state-of-the-art methods, achieving higher or comparable backdoor performance and MA across various datasets with limited PMC. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Prototypical Replay with Old-class Focusing knowledge Distillation for Incremental Named Entity Recognition 39

Prototypical Replay with Old-class Focusing Knowledge Distil...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Zesheng Zhu, Qiannan Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application MOE China

ISBN: (纸本)157735897X

Catastrophic forgetting is a key challenge in incremental named entity recognition (INER). Existing methods often address this issue through distillation-based approaches, which involve transferring previously learned knowledge from the old model to the new one. However, these methods may not fully equip the new model with an adequate understanding of the characteristics about old entity types, leading to confusion when classifying tokens associated with these entity types. To address this challenge, we propose a novel method called Prototypical Replay with Old-class Focusing knowledge Distillation (POF) for INER. Our approach focuses on preserving the main characteristics of each previous entity type by storing compact prototypes and replaying them with appropriate frequency. This replay strategy makes the new model review the knowledge of old entity types while minimizing storage needs. Additionally, we introduce an old-class focusing knowledge distillation (OFKD) loss, which distills features only in old-class regions to maintain the quality of old-class prototypes and prevent ineffective prototypical replay while preserving sufficient plasticity for learning new entity types. We conduct experiments on three benchmark datasets (i.e., Few-NERD, I2B2 and OntoNotes5), and the results demonstrate that our method outperforms all previous state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pan-media liquid metal 3D printing

引用

The Innovation 2025年第4期6卷 7-8页

作者： Xiaohui Shan Weichen Feng Minghui Guo Xuelin Wang Jing Liu School of Biomedical Engineering Tsinghua UniversityBeijing 100084China Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and ChemistryChinese Academy of SciencesBeijing 100190China Beijing Advanced Innovation Center for Biomedical Engineering Beijing Advanced Innovation Center for Big Data-Based Precision MedicineSchool of Engineering MedicineBeihang UniversityBeijing 100191China

INTRODUCTION The manufacturing industry has evolved from traditional forging and cutting to three-dimensional(3D)printing,a revolutionary technology that expands human imagination by creating everything of complex shapes and intricate structures,making it a cornerstone of smart manufacturing.1 However,conventional fabrications may encounter bottlenecks that seriously restrict their printing across different inks,ambient,and *** existing 3D printing methods to produce target functional components on diverse working media,therefore,requires significant *** highly adaptable 3D printing inks,liquid metals(LMs)open large spaces to address such challenges due to their versatile capabilities,such as fluidities,conductivities,easy solid-liquid transitions,and *** continuous efforts are being increasingly made in LM printing in different media,2 there is still no generalized methodology or concept proposed to unite all LM 3D printing techniques,inks,and media *** achieve this intriguing target,here we present a unified 3D printing concept,termed pan-media liquid metal 3D printing,to manufacture customized end-user devices as ***-media 3D printing means that it is able to administrate printing with any ink and any working ambient,from gases and liquids to soft matters,bio-tissues,and rigid media,transcending the boundaries of traditional printing ***,with intentionally introduced physical or chemical processing between LM inks and ambient,pan-media LM 3D printing could achieve a much wider variety of 3D object and targeted functions over existing *** synthesizing the pan-media theory of LM 3D printing,we prospect a pan-media manufacturing center equipped with functional ink storage,media library,printing head system,and control units,all integrated to fully address the desired printing tasks.

关键词： expands human imagination Liquid metals creating everything complex shapes intricate forging cutting smart manufacturing d printing produce target functional com D printing

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Mixed Traffic Flow with Connected and Autonomous Vehicles Based on Simplified DSM Model 23

Stability Analysis of Mixed Traffic Flow with Connected and ...

引用

23rd COTA International Conference of Transportation Professionals: Emerging data-Driven Sustainable Technological Innovation in Transportation, CICTP 2023

作者： Long, Wenmin Lu, Guangquan Liu, Miaomiao Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beihang Univ. Beijing China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beihang Univ. Beijing China

ISBN: (数字)9780784485040

ISBN: (纸本)9780784485040

The applications of mobile communication and automatic driving-related technologies in transportation have made a revolution for us in traffic information perception, vehicle cooperative control, and traffic management. Besides, the emergence and development of connected vehicles (CV) and connected and autonomous vehicles (CAV) have gradually changed the traditional traffic flow into a mixed one. In order to investigate their influences and characteristics of mixed traffic flows, this paper constructs an analysis model to derive the linear stability condition of the mixed traffic flow with CV and CAV based on the simplified desired safety margin (SDSM) model. Several numerical experiments are conducted to analyze the string stability of homogeneous and heterogeneous traffic flow, respectively. The results reveal that the presence of CAV could contribute to improving the string stability as well as reducing rear-end crashes. The higher the penetration rate of CAV, the more stable the string. And the time delay in drivers and communications is not conducive to the string stability. Besides, it is also found that controllable vehicles show great potential in preventing shockwave formation and propagation, suggesting a new way in traffic flow management. © ASCE.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple Robots

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1452-1463页

作者： Mei Liu Xiaoyan Zhang Mingsheng Shang Long Jin School of Information Science and Engineering Lanzhou UniversityLanzhou 730000 State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810016China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Shenzhen Research Institute Lanzhou UniversityShenzhen 518063China

Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)*** obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA ***,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ***,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.

关键词： Consensus filter k-winners-take-all(kWTA) multirobot coordination noise resistance

来源：评论

学校读者我要写书评

暂无评论

Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading 39

Like an Ophthalmologist: Dynamic Selection Driven Multi-View...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Federated Incremental Named Entity Recognition 31

Federated Incremental Named Entity Recognition

引用

31st International Conference on Computational Linguistics, COLING 2025

ISBN: (纸本)9798891761964

Federated learning-based Named Entity Recognition (FNER) has attracted widespread attention through decentralized training on local clients. However, most FNER models assume that entity types are pre-fixed, so in practical applications, local clients constantly receive new entity types without enough storage to access old entity types, resulting in severe forgetting on previously learned knowledge. In addition, new clients collecting only new entity types may join the global training of FNER irregularly, further exacerbating catastrophic forgetting. To overcome the above challenges, we propose a Forgetting-Subdued Learning (FSL) model which solves the forgetting problem on old entity types from both intra-client and inter-client two aspects. Specifically, for intra-client aspect, we propose a prototype-guided adaptive pseudo labeling and a prototypical relation distillation loss to surmount catastrophic forgetting of old entity types with semantic shift. Furthermore, for inter-client aspect, we propose a task transfer detector. It can identify the arrival of new entity types that are protected by privacy and store the latest old global model for relation distillation. Qualitative experiments have shown that our model has made significant improvements compared to several baseline methods. © 2025 Association for Computational Linguistics.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation 39

Causal-Inspired Multitask Learning for Video-Based Human Pos...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

ISBN: (纸本)157735897X

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multi-task 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：