检索结果-内蒙古大学图书馆

Rethinking the Sample Relations for Few-Shot Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yin, Guowei Huang, Sheng Huangfu, Luwen Zhang, Yi Zhang, Xiaohong School of Big Data and Software Engineering Chongqing University No.55 Daxuecheng South Rd. Shapingba Chongqing401331 China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University No.174 Shazhengjie Shapingba Chongqing400044 China Fowler College of Business San Diego State University San DiegoCA92182 United States San Diego State University San DiegoCA92182 United States AI4Business Lab San Diego State University San DiegoCA92182 United States

Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that capture semantic information and has achieved remarkable success in Few-Shot Learning (FSL). Nevertheless, current few-shot contrastive learning approaches often overlook the semantic similarity discrepancies at different granularities when employing the same modeling approach for different sample relations, which limits the potential of few-shot contrastive learning. In this paper, we introduce a straightforward yet effective contrastive learning approach, Multi-Grained Relation Contrastive Learning (MGRCL), as a pretraining feature learning model to boost few-shot learning by meticulously modeling sample relations at different granularities. MGRCL categorizes sample relations into three types: intra-sample relation of the same sample under different transformations, intra-class relation of homogenous samples, and inter-class relation of inhomogeneous samples. In MGRCL, we design Transformation Consistency Learning (TCL) to ensure the rigorous semantic consistency of a sample under different transformations by aligning predictions of input pairs. Furthermore, to preserve discriminative information, we employ Class Contrastive Learning (CCL) to ensure that a sample is always closer to its homogenous samples than its inhomogeneous ones, as homogenous samples share similar semantic content while inhomogeneous samples have different semantic content. Our method is assessed across four popular FSL benchmarks, showing that such a simple pre-training feature learning method surpasses a majority of leading FSL methods. Moreover, our method can be incorporated into other FSL methods as the pre-trained model and help them obtain significant performance gains. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

Temperature prediction modeling and control parameter optimization based on data driven 5

学校读者我要写书评

暂无评论

Temperature prediction modeling and control parameter optimi...

5th IEEE International Conference on data Science in Cyberspace, DSC 2020

作者： Liu, Qingguang Wei, Jielong Lei, Sining Huang, Qingbao Zhang, Mengqiao Zhou, Xiongbin Guangxi University School of Electrical Engineering Nanning China School of EE Guangxi University China School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Alnan Aluminium Lnc. Alnan Aluminium Co. Ltd Nanning China

ISBN: (数字)9781728195582

ISBN: (纸本)9781728195582

The aluminum smelting process is characterized with multi-variable, strong coupling and large lag, which leads to low efficiency and high energy consumption. Previous study shows that Extreme learning machine (ELM) can be used to model furnace temperature for its high train speed. However, due to the random initialization of the input weight and the hidden layer threshold in the ELM, the furnace temperature prediction model is unstable in the start of each smelting process. To improve the stability, we introduce the restricted Boltzmann machine to optimize an ELM model. In addition, a furnace temperature segmentation optimization strategy based on whale optimization algorithm is proposed to effectively find the optimal values of the control parameters in each furnace temperature section. The simulation results state that the aluminum melting time can be reduced by about 6.67% after optimization. © 2020 IEEE.

关键词： Optimization

Lung Nodule Segmentation and Uncertain Region Prediction with an Uncertainty-Aware Attention Mechanism

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Han Wang, Qiuli Zhang, Yue An, Zhulin Chen, Liu Zhang, Xiaohong Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China The Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Radiology The First Affiliated Hospital of Army Medical University Chongqing400032 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China Institute of Computing Technology Beijing100190 China

Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty. Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations. However, these approaches fail to leverage the valuable information inherent in the consensus and disagreements among the multiple annotations. In this paper, we propose an Uncertainty-Aware Attention Mechanism (UAAM) that utilizes consensus and disagreements among multiple annotations to facilitate better segmentation. To this end, we introduce the Multi-Confidence Mask (MCM), which combines a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. The LC mask indicates regions with low segmentation confidence, where radiologists may have different segmentation choices. Following UAAM, we further design an Uncertainty-Guide Multi-Confidence Segmentation Network (UGMCS-Net), which contains three modules: a Feature Extracting Module that captures a general feature of a lung nodule, an Uncertainty-Aware Module that produces three features for the annotations’ union, intersection, and annotation set, and an Intersection-Union Constraining Module that uses distances between the three features to balance the predictions of final segmentation and MCM. To comprehensively demonstrate the performance of our method, we propose a Complex Nodule Validation on LIDC-IDRI, which tests UGMCS-Net’s segmentation performance on lung nodules that are difficult to segment using common methods. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules that are difficult to segment using conventional methods. © 2023, CC BY-NC-ND.

关键词： Computerized tomography

Learning embeddings of a heterogeneous behavior network for potential behavior prediction

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic engineering 2020年第3期21卷 422-436页

作者： Yue-yang WANG Wei-hao JIANG Shi-liang PU Yue-ting ZHUANG College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China School of Big Data&Software Engineering Chongqing UniversityChongqing 401331China Hikvision Research Institute Hangzhou Hikvision Digital Technology Co.Ltd.Hangzhou 310051China

Potential behavior prediction involves understanding the latent human behavior of specific groups,and can assist organizations in making strategic *** in information technology has made it possible to acquire more and more data about human *** this paper,we examine behavior data obtained in realworld scenarios as an information network composed of two types of objects(humans and actions)associated with various attributes and three types of relationships(human-human,human-action,and action-action),which we call the heterogeneous behavior network(HBN).To exploit the abundance and heterogeneity of the HBN,we propose a novel network embedding method,human-action-attribute-aware heterogeneous network embedding(a4 HNE),which jointly considers structural proximity,attribute resemblance,and heterogeneity *** on two real-world datasets show that this approach outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.

关键词： Network embedding Representation learning Human behavior Social networks Heterogeneous information network Attribute

AdaXpert: Adapting neural architecture for growing data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Niu, Shuaicheng Wu, Jiaxiang Xu, Guanghui Zhang, Yifan Guo, Yong Zhao, Peilin Wang, Peng Tan, Mingkui School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Tencent AI Lab China National University of Singapore Singapore Northwestern Polytechnical University China Pazhou Laboratory China

In real-world applications, data often come in a growing manner, where the data volume and the number of classes may increase dynamically. This will bring a critical challenge for learning: given the increasing data volume or the number of classes, one has to instantaneously adjust the neural model capacity to obtain promising performance. Existing methods either ignore the growing nature of data or seek to independently search an optimal architecture for a given dataset, and thus are incapable of promptly adjusting the architectures for the changed data. To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data. Specifically, we introduce an architecture adjuster to generate a suitable architecture for each data snapshot, based on the previous architecture and the different extent between current and previous data distributions. Furthermore, we propose an adaptation condition to determine the necessity of adjustment, thereby avoiding unnecessary and time-consuming adjustments. Extensive experiments on two growth scenarios (increasing data volume and number of classes) demonstrate the effectiveness of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Resource Allocation Strategy of Internet of Vehicles Using Reinforcement Learning in Edge Computing Environment

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Li, Yihong Liu, Zhengli Tao, Qi School of Computer Science and Software School of Big Data Zhaoqing University Guangdong Zhaoqing526000 China School of Computer Science Wuhan University Hubei Wuhan430000 China School of Cyber of Science and Engineering Wuhan University Hubei Wuhan430000 China

Because the traditional computing model can no longer meet the particularity of Internet of Vehicles tasks, aiming at its characteristics of high bandwidth, low latency and high reliability, this paper proposes a resource allocation strategy for Internet of Vehicles using reinforcement learning in edge cloud computing environment. First, a multi-layer resource allocation model for Internet of Vehicles is proposed, which uses the cooperation mode of edge cloud computing servers and roadside units to dynamically coordinate edge computing and content caching. Then, based on the construction of communication model, calculation model and cache model, make full use of idle resources in Internet of Vehicles to minimize network delay under the condition of limited energy consumption. Finally, the optimization goal is solved by two-layer deep Q network model, and the best resource allocation plan is obtained. The simulation results based on the Internet of Vehicles model show that the computational energy consumption and system delay of proposed strategy do not exceed 400J and 600ms respectively. Besides, the overall effect of resource allocation is better than other comparison strategies and it has certain application prospects. © 2021, CC BY.

关键词： Energy utilization

Traffic flow prediction using SPGAPSO-CKRVM model

学校读者我要写书评

暂无评论

Revue d'Intelligence Artificielle 2020年第3期34卷 257-265页

作者： Lin, Hao Li, Leixiao Wang, Hui Wang, Yongsheng Ma, Zhiqiang College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service Hohhot010080 China

Traffic flow prediction is popular research of ITS. Traffic flow prediction models based on machine learning have recently been widely applied. In this study, we use machine learning algorithms, heuristic algorithms, and parallelization technology to propose a traffic flow prediction model based on Relevance Vector Machine called Genetic Algorithm and Particle Swarm Optimization based on spark parallelization optimized Combined kernel RVM (SPGAPSO-CKRVM). First, combined kernel functions are constructed based on common kernel functions. Second, a parameter optimization algorithm is proposed to optimize the parameters of combined kernel functions by Genetic Algorithm and Particle Swarm Optimization. To reduce time consumed by the parameter optimization algorithm, we parallel the parameter optimization algorithm by Spark. Finally, the proposed model is verified with the real data of Whitemud Drive in Canada. The experimental results indicate that SPGAPSO-CKRVM has greater accuracy than other prediction models and parallelization technology reduce time consumed by the parameter optimization algorithm significantly. © 2020 Lavoisier. All rights reserved.

关键词： Heuristic algorithms

Graph convolutional module for temporal action localization in videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zeng, Runhao Huang, Wenbing Tan, Mingkui Rong, Yu Zhao, Peilin Huang, Junzhou Gan, Chuang The School of Software Engineering South China University of Technology The Pazhou Laboratory Guangzhou China China The School of Software Engineering South China University of Technology The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Tencent AI Laboratory Shenzhen China The MIT-IBM Watson AI Lab CambridgeMA02142 United States

Temporal action localization, which requires a machine to recognize the location as well as the category of action instances in videos, has long been researched in computer vision. The main challenge of temporal action localization lies in that videos are usually long and untrimmed with diverse action contents involved. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage methods) and then perform action recognition/regression on each of them individually, without explicitly exploiting their relations during learning. In this paper, we claim that the relations between action units play an important role in action localization, and a more powerful action detector should not only capture the local content of each action unit but also allow a wider field of view on the context related to it. To this end, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms. To be specific, we first construct a graph, where each action unit is represented as a node and their relations between two action units as an edge. Here, we use two types of relations, one for capturing the temporal connections between different action units, and the other one for characterizing their semantic relationship. Particularly for the temporal connections in two-stage methods, we further explore two different kinds of edges, one connecting the overlapping action units and the other one connecting surrounding but disjointed units. Upon the graph we built, we then apply graph convolutional networks (GCNs) to model the relations among different action units, which is able to learn more informative representations to enhance action localization. Experimental results show that our GCM consistently improves the performance of existing action localization methods, including two-stage methods

关键词： Convolution

Research on Optimization Strategy of Cold-chain Logistics Car Scheduling

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1910卷

作者： Aimin Yang Jie Liu Yue Wang College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China

In this paper, aiming at the vehicle information supervision problem existing in the transportation process of the third-party small and medium-sized cold chain logistics enterprises, combined with the actual monitoring demand of the vehicle, the cold chain logistics vehicle dynamic monitoring system is designed, and the vehicle scheduling optimization algorithm in the system is carried out. The study. In the aspect of vehicle scheduling in the system, an optimized genetic algorithm is used to find the optimal transportation path and reduce the transportation cost before transportation by planning the transportation sequence and path of the site.

关键词：