检索结果-内蒙古大学图书馆

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Su, Yukun Lin, Guosheng Hao, Yun Cao, Yiwen Wang, Wenjun Wu, Qingyao South China Univ Technol Sch Software & Engn Guangzhou Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Minist Educ Key Lab Big Data & Intelligent Robot Beijing Peoples R China Pazhou Lab Guangzhou Peoples R China

ISBN: (纸本)9781577358763

Object localization aims to generate a tight bounding box for the target object, which is a challenging problem that has been deeply studied in recent years. Since collecting bounding-box labels is time-consuming and laborious, many researchers focus on weakly supervised object localization (WSOL). As the recent appealing self-supervised learning technique shows its powerful function in visual tasks, in this paper, we take the early attempt to explore unsupervised object localization by self-supervision. Specifically, we adopt different geometric transformations to image and utilize their parameters as pseudo labels for self-supervised learning. Then, the class-agnostic activation map is used to highlight the target object potential regions. However, such attention maps merely focus on the most discriminative part of the objects, which will affect the quality of the predicted bounding box. Based on the motivation that the activation maps of different transformations of the same image should be equivariant, we further design a siamese network that encodes the paired images and propose a joint graph partition mechanism in an unsupervised manner to enhance the object co-occurrent regions. To validate the effectiveness of the proposed method, extensive experiments are conducted on CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets. Experimental results show that our method outperforms state-of-the-art methods using the same level of supervision, even outperforms some weakly-supervised methods.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Swarm robots Decentralized Control using Reinforcement Learning Stepwise Training Method in the Encircling Task

Swarm Robots Decentralized Control using Reinforcement Learn...

引用

2022 Global Conference on robotics, Artificial Intelligence and Information Technology, GCRAIT 2022

作者： Liu, Yang Wang, Xu Nie, Yiming Dai, Bin Zhu, Qi Shang, Erke College of Intelligence Science and Technology National University of Defence Technology Changsha China Xi'An Key Laboratory of Big Data and Intelligent Vision Xidian University Xi'an China National Innovation Institute of Defense Technology Beijing China

ISBN: (数字)9781665481922

ISBN: (纸本)9781665481922

We consider a special multiple-robot task, pursuit-evasion (PE) game, in which a swarm of hunting robots (Pursuers) attempts to encircle a target robot (Evader) in a two-dimensional plane with some fixed obstacles on it. Instead of the central control method, we suggest a fully decentralized pursuit strategy generated by the deep reinforcement learning (DRL) which has greatly advanced the research in decision-making field in recent years. While the DRL method in this encircling task faces a sparse reward and a nonconvex space challenge which makes convergence result unacceptable. In this article, we have clarified the definition of a successful encirclement by escaping angel. In order to overcome the inefficient exploration and premature convergence caused by the above challenges during the training process, we use a stepwise training method of an adaptive various reward function. All prosecutors use the same policy given by stepwise training method and the multi-agent deep deterministic policy gradient (MADDPG) algorithms. Simulations and comparisons are provided to validate the effectiveness of this work. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Tensor-Based Markov Chain Model for Heterogeneous Information Network Collective Classification

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2022年第9期34卷 4063-4076页

作者： Han, Chao Chen, Jian Tan, Mingkui Ng, Michael K. Wu, Qingyao Guangxi Univ Sch Elect Engn Nanning 530004 Guangxi Peoples R China South China Univ Technol Sch Software Engn Minist Educ Guangzhou 510641 Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou 510641 Peoples R China Univ Hong Kong Dept Math Hong Kong Peoples R China

Heterogeneous Information Network (HIN) collecitve classification studies the problem of predicting labels for one type of nodes in a HIN which contains multiple types of nodes multiple types of links among them. Previous studies have revealed that exploiting relative importance of links is quite useful to improve node classification performance as connected nodes tend to have similar labels. Most existing approaches exploit the relative importance of links either by directly counting the number of connections among nodes or by learning the weight of each type of link from labeled data only. However, these approaches either neglect the importance of types of links to the class labels or may lead to overfitting problem. We propose a Tensor-based Markov chain (T-Mark) approach, which is able to automatically and simultaneously predict the labels for unlabeled nodes and give the relative importance of types of links that actually improve the classification accuracy. Specifically, we build two tensor equations by using the HIN and features of nodes from both labeled and unlabeled data. A Markov chain-based model is proposed and it is solved by an iterative process to obtain the stationary distributions. Theoretical analyses of the existence and uniqueness of such probability distributions are given. Extensive experimental results demonstrate that T-Mark is able to achieve superior performance in the comparison and obtain reasonable relative importance of links.

关键词： Tensors Task analysis Probability distribution Classification algorithms Arrays Visualization Training data Heterogeneous information network node classification relative importance of links tensor Markov chain iterative algorithm

来源：评论

学校读者我要写书评

暂无评论

A Spatiotemporal Analysis of Age of Information at V2X-enabled Intersection 23

A Spatiotemporal Analysis of Age of Information at V2X-enabl...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and big data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Wang, Yaying Tan, Guoping Zhou, Siyuan Yang, Dengsong Ni, Baili Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing China College of Computer and Information Hohai University Nanjing China Jiangsu Intelligent Transportation and Intelligent Driving Research Institute Nanjing China Jiangsu Expressway Company Limited China

ISBN: (纸本)9781665494571

Ensuring the freshness of information is of importance to autonomous vehicles at vehicle-to-everything (V2X)-enabled intersection. In this paper we theoretically investigate the Age of information (AoI) at V2X-enabled suburban intersections and urban intersections. Specifically, we model the locations of connected vehicles by using stochastic geometry and consider a last-come first-serve discipline with preemption. Then we analyze the moments and distribution of the conditional successful probability and the conditional average AoI. Finally, we obtain the moments and the distribution of conditional average AoI. The accuracy of theoretical derivation is verified via simulations. Our numerical results show the influence of different parameters on the average AoI and the theoretical analysis provides a useful guideline for further system design. © 2021 IEEE.

关键词： Transmitters Smart cities Roads Stochastic processes Receivers Information age Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

An Enhanced-Precision Bandgap Reference Incorporating Temperature-Compensation

An Enhanced-Precision Bandgap Reference Incorporating Temper...

引用

Semiconductor and Electronic Technology (ISSET), International Symposium on

作者： Tianzi Xiang Quanyuan Xu Haorui Liu Ying Lu Southwest Forestry University College of Big Data and Intelligent Engineering Kunming Yunnan China Key Laboratory of Forestry and Ecological Big Data State Forestry Administration Southwest Forestry University Kunming Yunnan China Changchun University of Science and Technology School of Physics Changchun Jilin China

ISBN: (数字)9798350390285

ISBN: (纸本)9798350390292

In this work, an Enhanced-Precision Bandgap Reference Incorporating Temperature-Compensation was proposed. Unlike traditional bandgap references, the reference voltage output of 0.701 V is realized by combining reference current and resistor. Meanwhile, an innovative Linear-piecewise current compensation was proposed, which aimed at optimizing the temperature drift of the bandgap reference. The simulation results shows that the proposed curvature-compensation technique improves the TC from 24.96 to 2.14 $\text{ppm}/^{\circ}\mathrm{C}$ in the temperature range of $-40 \ {}^{\circ}\mathrm{C}$ to $120 \ {}^{\circ}\mathrm{C}$ ; the PSRR of Enhanced-Precision Bandgap Reference at low frequency is 72.40 dB; the line regulation is about 0.08 %/V for input voltages between 3.2 and 3.7 V in standard 0.18 μm 1P6M CMOS process. The proposal of this new circuit provides a new idea for the realization of high- performance integrated circuits in the future.

关键词： Resistors Integrated circuits Temperature distribution Photonic band gap Simulation CMOS process Regulation Proposals Voltage control Standards

来源：评论

学校读者我要写书评

暂无评论

Discrimination-Aware Network Pruning for Deep Model Compression

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第8期44卷 4035-4051页

作者： Liu, Jing Zhuang, Bohan Zhuang, Zhuangwei Guo, Yong Huang, Junzhou Zhu, Jinhui Tan, Mingkui South China Univ Technol Sch Software Engn Guangzhou 510641 Peoples R China South China Univ Technol Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou 510641 Peoples R China Monash Univ Fac Informat Technol Clayton Vic 3800 Australia Tencent AI Lab Shenzhen 518064 Peoples R China Pazhou Lab Guangzhou 510335 Peoples R China

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. To this end, we first introduce additional discrimination-aware losses into the network to increase the discriminative power of the intermediate layers. Next, we select the most discriminative channels for each layer by considering the discrimination-aware loss and the reconstruction error, simultaneously. We then formulate channel pruning as a sparsity-inducing optimization problem with a convex objective and propose a greedy algorithm to solve the resultant problem. Note that a channel (3D tensor) often consists of a set of kernels (each with a 2D matrix). Besides the redundancy in channels, some kernels in a channel may also be redundant and fail to contribute to the discriminative power of the network, resulting in kernel level redundancy. To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to further compress deep networks by removing redundant kernels. To avoid manually determining the pruning rate for each layer, we propose two adaptive stopping conditions to automatically determine the number of selected channels/kernels. The proposed adaptive stopping conditions tend to yield more efficient models with better performance in practice. Extensive experiments on both image classification and face recognition demonstrate th

关键词： Kernel Computational modeling Quantization (signal) Training Adaptation models Acceleration Redundancy Channel pruning kernel pruning network compression deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NID-SLAM: Neural Implicit Representation-based RGB-D SLAM In Dynamic Environments

arXiv

引用

arXiv 2024年

作者： Xu, Ziheng Niu, Jianwei Li, Qingfeng Ren, Tao Chen, Chen School of Computer Science Beihang University Beijing China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Big Data and Industrial Intelligent Networking Laboratory Hangzhou Innovation Institute of Beihang University Hangzhou China

Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving objects. In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments. We propose a new approach to enhance inaccurate regions in semantic masks, particularly in marginal areas. Utilizing the geometric information present in depth images, this method enables accurate removal of dynamic objects, thereby reducing the probability of camera drift. Additionally, we introduce a keyframe selection strategy for dynamic scenes, which enhances camera tracking robustness against large-scale objects and improves the efficiency of mapping. Experiments on publicly available RGB-D datasets demonstrate that our method outperforms competitive neural SLAM approaches in tracking accuracy and mapping quality in dynamic environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Sequential Three-Way Group Decision-Making for Double Hierarchy Hesitant Fuzzy Linguistic Term Set

SSRN

引用

SSRN 2024年

作者： Luo, Nanfang Zhang, Qinghua Xie, Qin Wang, Yutai Yin, Longjun Wang, Guoyin Chongqing Key Laboratory of Tourism Multisource Data Perception and Decision Ministry of Culture and Tourism Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Group decision-making (GDM) characterized by complexity and uncertainty is an essential part of various life *** research lacks tools to fuse information quickly and interpret decision results for partially formed *** limitation is particularly noticeable when there is a need to improve the efficiency of *** address this issue, a novel multi-level sequential three-way decision for group decision-making (S3W-GDM) model is constructed via granular *** model considers the vagueness, hesitation, and variation in the double hierarchy hesitant fuzzy linguistic term sets (DHHFLTS) GDM ***, for fusing information efficiently, a novel multi-level expert information fusion method is proposed, and the expert decision table and the extraction/aggregation of decision-leveled information based on the multi-level granularity are ***, the neighborhood theory, outranking relation and regret theory (RT) are utilized to redesign the calculations of conditional probability and relative loss function at each ***, the granular structure of DHHFLTS based on sequential three-way decision (S3WD) is defined, and the decision-making strategy and interpretation of decision-level are proposed. Furthermore, the algorithm of S3W-GDM model is ***, an illustrative example are presented, and the comparative and sensitivity analyses are performed to verify the superiority of this model. © 2024, The Authors. All rights reserved.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

arXiv

引用

arXiv 2025年

作者： Ou, Yixin Yao, Yunzhi Zhang, Ningyu Jin, Hui Sun, Jiacheng Deng, Shumin Li, Zhenguo Chen, Huajun Zhejiang University China Huawei Noah’s Ark Lab Canada National University of Singapore NUS-NCS Joint Lab Singapore Zhejiang Key Laboratory of Big Data Intelligent Computing China

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural computations. We address this issue through the lens of knowledge circuit evolution, identifying computational subgraphs that facilitate knowledge storage and processing. Our systematic analysis of circuit evolution throughout continual pre-training reveals several key findings: (1) the acquisition of new knowledge is influenced by its relevance to preexisting knowledge;(2) the evolution of knowledge circuits exhibits a distinct phase shift from formation to optimization;(3) the evolution of knowledge circuits follows a deep-to-shallow pattern. These insights not only advance our theoretical understanding of the mechanisms of new knowledge acquisition in LLMs, but also provide potential implications for improving continual pre-training strategies to enhance model performance Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

LogADCH: Hyperspheric-Based Log Message Anomaly Detection And Classification

LogADCH: Hyperspheric-Based Log Message Anomaly Detection An...

引用

Frontiers of robotics and Software Engineering (FRSE), International Conference on

作者： Shiming He Jinpan Xiao Bowen Chen Ying Lei School of Computer and Communication Engineering the Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science & Technology Changsha China

Web services have been integrated with all walks of life in society. Abnormalities in the network and services seriously affect user experience and company revenue. The system log records various information of the system, and the information-rich log messages usually show different anomalies. It is particularly important to accurately and timely identify the anomalies of the log messages and classify the anomalies. In addition, most of the current existing work only detects anomalies and does not classify them, and a few existing works require anomaly labels to classify anomalies. Based on these potential challenges, we propose an unsupervised hypersphere-based log message anomaly detection and classification method, LogADCH. We use the hypersphere loss function to let the BERT model learn compact representations of log messages and perform anomaly detection. Finally, K-Means clustering is performed on the semantic feature vectors detected as anomalies to form clusters of different types of anomalies. Compared with other works, LogADCH further classifies the abnormal types after detecting the abnormal logs, helping the operation and maintenance personnel to quickly locate the fault. We compare our method with other methods on two public datasets, and the experimental results show that LogADCH has superior performance in anomaly detection as well as anomaly classification.

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：