检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Yanglin Hu, Kai Zhang, Yuan Chen, Zhineng Gao, Xieping Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University China School of Computer Science Fudan University China Key Laboratory for Artificial Intelligence and International Communication Hunan Normal University China

ISBN: (纸本)157735897X

Current knowledge distillation (KD) methods for semantic segmentation focus on guiding the student to imitate the teacher’s knowledge within homogeneous architectures. However, these methods overlook the diverse knowledge contained in architectures with different inductive biases, which is crucial for enabling the student to acquire a more precise and comprehensive understanding of the data during distillation. To this end, we propose for the first time a generic knowledge distillation method for semantic segmentation from a heterogeneous perspective, named HeteroAKD. Due to the substantial disparities between heterogeneous architectures, such as CNN and Transformer, directly transferring cross-architecture knowledge presents significant challenges. To eliminate the influence of architecture-specific information, the intermediate features of both the teacher and student are skillfully projected into an aligned logits space. Furthermore, to utilize diverse knowledge from heterogeneous architectures and deliver customized knowledge required by the student, a teacher-student knowledge mixing mechanism (KMM) and a teacher-student knowledge evaluation mechanism (KEM) are introduced. These mechanisms are performed by assessing the reliability and its discrepancy between heterogeneous teacher-student knowledge. Extensive experiments conducted on three main-stream benchmarks using various teacher-student pairs demonstrate that our HeteroAKD outperforms state-of-the-art KD methods in facilitating distillation between heterogeneous architectures. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Problems and Analysis of Artificial Intelligence Specialty Construction in Universities Under the Present Situation of Artificial Intelligence Development 8th

The Problems and Analysis of Artificial Intelligence Special...

引用

8th EAI International Conference on e-Learning, e-Education, and Online Training, eLEOT 2022

作者： Fu, Weina Liu, Shuai Institute of Information Science and Engineering Hunan Normal University Hunan Changsha410081 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha410081 China

ISBN: (纸本)9783031211638

China’s independent innovation ability in the field of artificial intelligence is a key link to occupy the commanding heights of future science and technology and talent competition. The cultivation of artificial intelligent talents is crucial to promote the development of the artificial intelligent industry. There is a large demand for artificial intelligence talents in the market, but the development of artificial intelligence in colleges and universities is still faced with many problems, such as the construction of related disciplines and majors has just started, the strength of artificial intelligence teachers in colleges and universities is weak, the talent training is mainly based on postgraduate education and the education system is not perfect. This paper analyzes the current cultivation situation of artificial intelligence major in undergraduate colleges and vocational colleges, points out the shortcomings in the construction of artificial intelligence major, and gives some suggestions. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Novelty Detection-Based Automated Anomaly Identification via Optimized Deep Generative Model 9th

Novelty Detection-Based Automated Anomaly Identification via...

引用

9th CCF Conference on Big Data, BigData 2021

作者： Liu, Lianye Liu, Jinping Wu, Juanjuan Zhou, Jiaming Cai, Meiling Hunan Meteorological Science Institute Hunan Changsha410007 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Hunan Changsha410081 China

ISBN: (纸本)9789811697081

Novelty detection (ND) is a crucial task in machine learning to identify anomalies in the test data in some respects different from the training data. As an anomaly detection method, novelty detection only uses normal samples for model learning, which can well fit most of the natural scenes that the amount of abnormal samples is in fact strongly insufficient, such as network intrusion detection, industrial fault detection, and so on, due to the rareness of abnormal events or the high cost of abnormal samples collection. This paper proposes a reconstruction-based ND scheme by introducing an optimized deep generative model (ODGM), which combines the concept of Variational Auto-encoder (VAE) and the generative adversarial network (GAN) model jointly to efficiently and stably learn the essential characteristics from normal samples. A novelty index is established by combining signal reconstruction loss and feature loss between the original signal of the reconstructed signal based on the ODGM on normal samples for anomaly point identification in the test data. The effectiveness and superiority of the proposed model is validated and compared with other representative deep learning-based novelty detection models on two public data sets. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks

arXiv

引用

arXiv 2025年

作者： Li, Yinqi Chang, Hong Hou, Ruibing Shan, Shiguang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we extend the discriminative capability of pretrained frozen generative diffusion models from the classification task [1], [2] to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model. To this end, a gradient-based discrete optimization approach for replacing the heavy prediction enumeration process, and a prior distribution model for making more accurate use of the Bayes’ rule, are proposed respectively. Empirical results show that this method is on par with basic discriminative object detection baselines on COCO dataset. In addition, our method can greatly speed up the previous diffusion-based method [1], [2] for classification without sacrificing accuracy. Code and models are available at https://***/LiYinqi/DIVE. © 2025, CC BY-NC-ND.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Object Detection Algorithm with Multi-scale Context Information Based on YOLOv4 4

An Object Detection Algorithm with Multi-scale Context Infor...

引用

4th International Conference on Natural Language processing, ICNLP 2022

作者： Ma, Sugang An, Wen Yang, Xiaobao Hou, Zhiqiang Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China Xi'an University of Posts and Telecommunications School of Computer Science and Technology Xi'an China Xi'an University of Posts and Telecommunications Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Most current object detection algorithms have the issue of missing objects due to occlusion. As the great difference of scale between occlusion objects and their integrity is affected, how to reduce the missing rate of occlusion objects has become a challenging problem in object detection algorithms. Aiming at the problem, this paper proposes an object detection algorithm based on multi-scale context information on the basis of the YOLOv4 algorithm framework. Firstly, the object features are extracted through the CSPDarkNet53 feature extraction network. Then, the proposed attention-guided multi-scale context information module (AMCM) enhances the ability to perceive object context information and endows features with different influence factors through attention weighting to improve feature discrimination. The experimental results show that the detection accuracy and recall of the proposed algorithm reach 83.2% and 96.4% respectively on PASCAL VOC dataset, and 83.2% and 91% on KITTI dataset, which improves the detection performance of YOLOv4 algorithm. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Analysis on the Training Mode of Master Students in Artificial Intelligence Field for Electronic Information Professional Degree—Take Hunan Normal University as an Example 8th

An Analysis on the Training Mode of Master Students in Artif...

引用

8th EAI International Conference on e-Learning, e-Education, and Online Training, eLEOT 2022

ISBN: (纸本)9783031211638

The ability of independent innovation in the field of artificial intelligence is a key element to occupy the commanding heights of future technology and talent competition in China. The cultivation of artificial intelligence talents, especially the cultivation high-end talent, it is essential to promote the development of artificial intelligence industry. At present, the market for artificial intelligence talents is in great demand. There is a shortage of high-end artificial intelligence talents, the weak strength of artificial intelligence teachers in universities, and the incomplete education system for talent training and many other issues. This paper combines some measures taken by Hunan Normal University for graduate students in the field of artificial intelligence in the degree of electronic information, the necessity and feasibility of artificial intelligence training senior talents are discussed for social needs in the field of artificial intelligence, The training goals and methods of postgraduate students in the field of artificial intelligence under the professional category of electronic information major are clarified, and the construction of artificial intelligence field is planned. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Professional aspects

来源：评论

学校读者我要写书评

暂无评论

Set pair three-way overlapping community discovery algorithm for weighted social internet of things

引用

Digital Communications and Networks 2023年第1期9卷 3-13页

作者： Chunying Zhang Jing Ren Lu Liu Shouyue Liu Xiaoqi Li Liya Wang College of Science North China University of Science and TechnologyTangshanHebeiChina Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and TechnologyTangshanHebeiChina Hebei Key Laboratory of Data Science and Application North China University of Science and TechnologyTangshanHebeiChina The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and TechnologyTangshanHebeiChina Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and TechnologyTangshanHebeiChina

There are many problems in Social Internet of Things(IoTs),such as complex topology information,different degree of association between nodes and overlapping *** idea of set pair information grain computing and clustering is introduced to solve the above problems so as to accurately describe the similarity between nodes and fully explore the multi-community structure.A Set Pair Three-Way Overlapping Community Discovery Algorithm for Weighted Social Internet of Things(WSIoT-SPTOCD)is *** the local network structure,which fully considers the topological information between nodes,the set pair connection degree is used to analyze the identity,difference and reverse of neighbor *** similarity degree of different neighbor nodes is defined from network edge weight and node degree,and the similarity measurement method of set pair between nodes based on the local information structure is *** to the number of nodes'neighbors and the connection degree of adjacent edges,the clustering intensity of nodes is defined,and an improved algorithm for initial value selection of k-means is *** nodes are allocated according to the set pair similarity between nodes and different ***-way community structures composed of a positive domain,boundary domain and negative domain are generated ***,the overlapping node set is generated according to the calculation results of community node ***,experiments are carried out on artificial networks and real *** results show that WSIoT-SPTOCD performs well in terms of standardized mutual information,overlapping community modularity and F1.

关键词： Social internet of things Set pair analysis K-means Local information structure Overlapping community

来源：评论

学校读者我要写书评

暂无评论

EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion 39

EDGE: Unknown-aware Multi-label Learning by Energy Distribut...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yuchen Xu, Qianqian Wang, Zitai Yang, Zhiyong He, Junwei 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

ISBN: (纸本)157735897X

Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is crucial to model the joint information among classes. To this end, JointEnergy, which is a representative multi-label OOD inference criterion, summarizes the logits of all the classes. However, we find that JointEnergy can produce an imbalance problem in OOD detection, especially when the model lacks enough discrimination ability. Specifically, we find that the samples only related to minority classes tend to be classified as OOD samples due to the ambiguous energy decision boundary. Besides, imbalanced multi-label learning methods, originally designed for ID ones, would not be suitable for OOD detection scenarios, even producing a serious negative transfer effect. In this paper, we resort to auxiliary outlier exposure (OE) and propose an unknown-aware multi-label learning framework to reshape the uncertainty energy space layout. In this framework, the energy score is separately optimized for tail ID samples and unknown samples, and the energy distribution gap between them is expanded, such that the tail ID samples can have a significantly larger energy score than the OOD ones. What's more, a simple yet effective measure is designed to select more informative OE datasets. Finally, comprehensive experimental results on multiple multi-label and OOD datasets reveal the effectiveness of the proposed method. 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

High-accurate and efficient numerical algorithms for the self-consistent field theory of liquid-crystalline polymers

引用

Computers & Mathematics with Applications 2025年 194卷 31-52页

作者： Zhijuan He Kai Jiang Liwei Tan Xin Wang Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Xiangtan Hunan 411105 China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai 200240 China

Self-consistent field theory (SCFT) is one of the most widely-used frameworks in studying the equilibrium phase behavior of inhomogeneous polymers. For liquid-crystalline polymeric systems, the primary numerical challenges in solving SCFT involve efficiently solving a large number of 6-dimensional (6D, 3D space + 2D orientation + 1D contour) partial differential equations (PDEs), accurately determining subtle energy differences between self-assembled structures, and developing effective iterative methods for nonlinear SCFT iterations. To address these challenges, this work introduces a suite of high-order and efficient numerical methods tailored to SCFT of liquid-crystalline polymers. These methods include various advanced PDE solvers, an improved Anderson iteration algorithm to accelerate SCFT calculations, and an optimization technique for adjusting the computational domain during SCFT iterations. Extensive numerical tests demonstrate the efficiency of the proposed methods. Based on these algorithms, we further explore the self-assembly behavior of liquid-crystalline polymers through 4D, 5D, and 6D simulations, uncovering intricate 3D spatial structures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unknown Type Streaming Feature Selection via Maximal Information Coefficient

Unknown Type Streaming Feature Selection via Maximal Informa...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Peng Zhou Yunyun Zhang Yuanting Yan Shu Zhao Key Laboratory of Intelligent Computing and Signal Processing (the Ministry of Education of China) School of Computer Science and Technology Anhui University Hefei China

Feature selection aims to select an optimal minimal feature subset from the original datasets and has become an indispensable preprocessing component before data mining and machine learning, especially in the era of big data. Most feature selection methods implicitly assume that we can know the feature type (categorical, numerical, or mixed) before learning, then design corresponding measurements to calculate the correlation between features. However, in practical applications, features may be generated dynamically and arrive one by one over time, which we call streaming features. Most existing streaming feature selection methods assume that all dynamically generated features are the same type or assume we can know the feature type for each new arriving feature on the fly, but this is unreasonable and unrealistic. Therefore, this paper firstly studies a practical issue of Unknown Type Streaming Feature Selection and proposes a new method to handle it, named UT-SFS. Extensive experimental results indicate the effectiveness of our new method. UT-SFS is nonparametric and does not need to know the feature type before learning, which aligns with practical application needs.

关键词： Measurement Microwave integrated circuits Correlation Conferences Machine learning Big Data Feature extraction

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：