检索结果-内蒙古大学图书馆

Semi-Discrete Optimal Transport for Long-Tailed Classification

计算机科学技术学报（英文版） 2025年第1期40卷 252-266页

作者：金连宝雷娜罗钟铉吴瑾艾超顾险峰 School of Mathematical Sciences Dalian University of Technology Dalian China International School of Information Science and Engineering Dalian University of Technology Dalian China School of Software Technology Dalian University of Technology Dalian China Huawei Technologies Co. Ltd Shenzhen China Department of Computer Science Stony Brook University New York USA

The long-tailed data distribution poses an enormous challenge for training neural networks in classification.A classification network can be decoupled into a feature extractor and a *** paper takes a semi-discrete opti-mal transport(OT)perspective to analyze the long-tailed classification problem,where the feature space is viewed as a continuous source domain,and the classifier weights are viewed as a discrete target *** classifier is indeed to find a cell decomposition of the feature space with each cell corresponding to one *** imbalanced training set causes the more frequent classes to have larger volume cells,which means that the classifier's decision boundary is biased towards less frequent classes,resulting in reduced classification performance in the inference ***,we propose a novel OT-dynamic softmax loss,which dynamically adjusts the decision boundary in the training phase to avoid overfitting in the tail *** addition,our method incorporates the supervised contrastive loss so that the feature space can satisfy the uniform distribution *** and comprehensive experiments demonstrate that our method achieves state-of-the-art performance on multiple long-tailed recognition benchmarks,including CIFAR-LT,ImageNet-LT,iNaturalist 2018,and Places-LT.

关键词： semi-discrete optimal transport long-tailed classification decision boundary supervised contrastive loss

来源：评论

学校读者我要写书评

暂无评论

DIEONet:Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition

引用

computers, Materials & Continua 2025年第3期82卷 5019-5033页

作者： Shaoqi Hou Zebang Qin Chenyu Wu Guangqiang Yin Xinzhong Wang Zhiguo Wang School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Visual Place Recognition(VPR)technology aims to use visual information to judge the location of agents,which plays an irreplaceable role in tasks such as loop closure detection and *** is well known that previous VPR algorithms emphasize the extraction and integration of general image features,while ignoring the mining of salient features that play a key role in the discrimination of VPR *** this end,this paper proposes a Domain-invariant Information Extraction and Optimization Network(DIEONet)for *** core of the algorithm is a newly designed Domain-invariant Information Mining Module(DIMM)and a Multi-sample Joint Triplet Loss(MJT Loss).Specifically,DIMM incorporates the interdependence between different spatial regions of the feature map in the cascaded convolutional unit group,which enhances the model’s attention to the domain-invariant static object *** Loss introduces the“joint processing of multiple samples”mechanism into the original triplet loss,and adds a new distance constraint term for“positive and negative”samples,so that the model can avoid falling into local optimum during *** demonstrate the effectiveness of our algorithm by conducting extensive experiments on several authoritative *** particular,the proposed method achieves the best performance on the TokyoTM dataset with a Recall@1 metric of 92.89%.

关键词： Visual place recognition domain-invariant information mining module multi-sample joint triplet loss

来源：评论

学校读者我要写书评

暂无评论

Application of optimized deformable convolution in underwater biological detection algorithm 3

Application of optimized deformable convolution in underwate...

引用

3rd International Symposium on computer Applications and Information Systems, ISCAIS 2024

作者： Zhuang, Hongwei Liu, Weisheng School of Computer and Software Engineering Liaoning University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781510681316

Underwater target detection is an important method for marine life detection. However, the accuracy of target detection and recognition is affected by the problems of image occlusion, blurred water quality and complex background of underwater targets. An improved YOLOV7 underwater biological target detection method is proposed to address the above problems. Firstly, the DCN structure is improved by incorporating the residual structure into the DCN, with new jump connections and 1×1 convolutional branches, so that the network can learn the residual information between the input and the output. It can improve the expressive ability of the model, reduce the number of parameters, and enhance the adaptability to the shape of the object. Finally, COT3 is integrated, which utilises a self-attention mechanism to weight the input feature maps so that the model can focus on important contextual information around the target and improve the model's ability to handle complex scenes. The experimental results show that the improved YOLOv7 model achieves an average detection accuracy mAP value of 80.4%, which is 2.8% higher than the original algorithm, and the algorithm is better than the original YOLOv7 algorithm in terms of detection accuracy and speed, which is more suitable for the detection of underwater targets. © 2024 SPIE.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Applied Technology Research on the Construction of Bidirectional Knowledge Graph Curriculum System Based on SmartKG 6

Applied Technology Research on the Construction of Bidirecti...

引用

6th International Workshop on Artificial Intelligence and Education, WAIE 2024

作者： Jiang, Su Luo, Wei Cui, Hengji School of Computer Science and Software Engineering Dalian Neusoft University of Information Dalian China

ISBN: (纸本)9798350378894

Amidst the rapid advancements in artificial intelligence technology, it is imperative to apply these technological developments to the realm of education to enhance information-based teaching methodologies. This article introduces a knowledge management framework that aims to visualize curriculum knowledge systems using knowledge graphs in the educational sector. Taking courses like Fundamentals of computer Systems as exemplars, the article demonstrates the techniques for constructing knowledge graphs. Additionally, SmartKG's ease of deployment and application allows students to construct their own visual knowledge graphs, fostering a deeper comprehension of knowledge and fostering the profound integration of AI and teaching. Through the analysis of the curriculum system and students' self-constructed knowledge graphs, the efficacy of utilizing knowledge graphs in learning has been validated, propelling the application and practice of intelligent classroom teaching. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Neural Operator-Based Framework for Time Efficient Denoising of Displacement Fields in Ultrasound Elastography

Neural Operator-Based Framework for Time Efficient Denoising...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhu, Yihong Peng, Bo School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China

ISBN: (纸本)9781665410205

In ultrasound elastography, the noise present in the measured displacement fields has been a critical factor affecting the quality of the strain or elastic distribution reconstruction. Existing partial differential equation (PDE) based denoising algorithms can effectively remove noise to some extent but are limited by slow solving speeds. To address this challenge, we introduce a neural operator-based framework for denoising measured displacement fields in ultrasound elastography. By utilizing neural operators to learn a general solution operator for the denoising equation, the framework aims to achieve fast and accurate denoising of displacement fields. Experiments conducted on simulated data and tissue-mimicking phantom data demonstrate that this method performs comparably to traditional methods across various metrics. In particular, the proposed approach achieves processing speeds approximately 30 to 577 times faster than the finite difference method (FDM) in various data dimensions, making it a highly effective solution for rapid and scalable data processing in ultrasound elastography. © 2024 IEEE.

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

Explainable-AI-based two-stage solution for WSN object localization using zero-touch mobile transceivers

引用

science China(Information sciences) 2024年第7期67卷 27-45页

作者： Kai FANG Junxin CHEN Han ZHU Thippa Reddy GADEKALLU Xiaoping WU Wei WANG School of Mathematics and Computer Science Zhejiang A&F University School of Software Dalian University of Technology Faculty of Applied Sciences Macao Polytechnic University Department of Electrical and Computer Engineering Lebanese American University School of Information Engineering Huzhou University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University

Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability, the interference factors in the process of WSN object localization cannot be effectively eliminated. In this paper, an explainable-AI-based two-stage solution is proposed for WSN object localization. In this solution, mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters. To address this,an explainable AI model is proposed to solve the localization problem. Since the relationship among the variables is difficult to fully include in the first-stage traditional model, we develop a two-stage explainable AI solution for this localization problem. The two-stage solution is actually a comprehensive consideration of the relationship between variables. The solution can continue to use the constraints unused in the firststage during the second-stage, thereby improving the performance of the solution. Therefore, the two-stage solution has stronger robustness compared to the closed-form solution. Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters. However, the two-stage solution performs better than the traditional solution, especially with a small number of mobile transceivers and sensors or in the presence of high noise. Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.

关键词： explainable AI object localization semidefinite relaxation mobile transceiver two-stage solution closed-form solution

来源：评论

学校读者我要写书评

暂无评论

ViF-SD2E: a robust weakly-supervised framework for neural decoding

引用

Neural Computing and Applications 2025年第9期37卷 6645-6661页

作者： Feng, Jingyi Luo, Yong Song, Shuang Hu, Han National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Neural decoding plays a vital role in the interaction between the brain and the outside world. Our task in this paper is to decode the movement track of a finger directly based on the neural data. Existing neural decoding solutions primarily perform some preprocessing operations on neural data before feeding them into existing models (such as LSTM) for decoding. However, these solutions either are prone to overfitting or cannot well exploit the spatial and temporal information. In our previous observations, there is a symmetrical phenomenon between the unsupervised decoded trajectory and the ground truth trajectory within the activity space. This precisely motivates us to propose (or derive) a robust weakly-supervised framework (or model structure), called ViF-SD2E, for neural decoding. In particular, it consists of a space-division (SD) module and an exploration–exploitation (2E) strategy, to effectively exploit both the spatial information of the outside world and the temporal information of neural activity, where the SD2E output is analogized with the weak 0/1 vision feedback (ViF) label for training. Extensive experiments demonstrate the effectiveness of our method, which can sometimes be comparable to supervised counterparts. Therefore, we redirect our attention to the information (hidden in data) ViF-SD2E conveys to us. In other words, we believe that the advantage of ViF-SD2E lies in the fact that its processing steps are objectively determined by the inherent attributes (i.e., symmetry) of the neural data, or rather, the model structure is fixed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Energy Optimization:Efficient Path Selection in Wireless Sensor Networks with Hybrid ANN

引用

computers, Materials & Continua 2024年第5期79卷 2945-2970页

作者： Muhammad Salman Qamar Ihsan ulHaq Amil Daraz Atif MAlamri Salman A.AlQahtani Muhammad Fahad Munir Department of Electrical and Computer Engineering International Islamic UniversityIslamabad44000Pakistan School of Information Science and Engineering NingboTech UniversityNingbo315100China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11495Saudi Arabia Computer Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11495Saudi Arabia

In pursuit of enhancing the Wireless Sensor Networks(WSNs)energy efficiency and operational lifespan,this paper delves into the domain of energy-efficient routing ***,the limited energy resources of Sensor Nodes(SNs)are a big challenge for ensuring their efficient and reliable *** data gathering involves the utilization of a mobile sink(MS)to mitigate the energy consumption problem through periodic network *** mobile sink(MS)strategy minimizes energy consumption and latency by visiting the fewest nodes or predetermined locations called rendezvous points(RPs)instead of all cluster heads(CHs).CHs subsequently transmit packets to neighboring *** unique determination of this study is the shortest path to reach *** the mobile sink(MS)concept has emerged as a promising solution to the energy consumption problem in WSNs,caused by multi-hop data collection with static *** this study,we proposed two novel hybrid algorithms,namely“ Reduced k-means based on Artificial Neural Network”(RkM-ANN)and“Delay Bound Reduced kmeans with ANN”(DBRkM-ANN)for designing a fast,efficient,and most proficient MS path depending upon rendezvous points(RPs).The first algorithm optimizes the MS’s latency,while the second considers the designing of delay-bound paths,also defined as the number of paths with delay over bound for the *** methods use a weight function and k-means clustering to choose RPs in a way that maximizes efficiency and guarantees network-wide *** addition,a method of using MS scheduling for efficient data collection is *** simulations and comparisons to several existing algorithms have shown the effectiveness of the suggested methodologies over a wide range of performance indicators.

关键词： Wireless Sensor Networks(WSNs) mobile sink(MS) rendezvous point(RP) machine learning Artificial Neural Networks(ANNs)

来源：评论

学校读者我要写书评

暂无评论

ATM-NeRF: Accelerating Training for NeRF Rendering on Mobile Devices via Geometric Regularization

引用

IEEE Transactions on Multimedia 2025年 27卷 3279-3293页

作者： Chen, Yang Zhang, Lin Zhao, Shengjie Zhou, Yicong Tongji University School of Software Engineering Shanghai201804 China Ministry of Education Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Shanghai201804 China University of Macau Department of Computer and Information Science 999078 China

Recently, an increasing number of researchers have been dedicated to transferring the impressive novel view synthesis capability of Neural Radiance Fields (NeRF) to resource-constrained mobile devices. One common solution is to pre-train NeRF and bake it into textured meshes which are well supported by mobile graphics hardware. However, the training process of existing methods often requires several hours even with multiple high-end NVIDIA V100 GPUs. The underlying reason is that these schemes mainly rely on photometric rendering loss, neglecting the geometric relationship between the pre-trained NeRF and the baked results. Standing on this point, we present ATM-NeRF (Accelerating Training for Mobile rendering based on NeRF), which is the first to apply effective geometric regularization constraints during both the pre-training and the baking training stages for faster convergence. Specifically, in the initial NeRF pre-training stage, we enforce consistency of the multi-resolution density grids representing the scene geometry to mitigate the shape-radiance ambiguity problem to some extent, achieving a coarse mesh with smoothness. In the second stage, we utilize the positions and geometric features of 3D points projected from the pre-trained posed depths to provide geometric supervision for joint refinement of geometry and appearance of the coarse mesh. As a result, our ATM-NeRF achieves comparable rendering quality to MobileNeRF with a training speed that is about 30× ∼ 70× faster while maintaining finer structure details of the exported mesh. Our source code and the demo video have been released at https://***/ATM-NeRF/. © 1999-2012 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

UKF‐MOT:An unscented Kalman filter‐based 3D multi‐object tracker

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 1031-1041页

作者： Meng Liu Jianwei Niu Yu Liu Collective Intelligence&Collaboration Laboratory China North Artificial Intelligence and Innovation Research InstituteBeijingChina China North Vehicle Research Institute BeijingChina State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijingChina State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijingChina School of Computer Science and Engineering Beihang UniversityBeijingChina

Multi‐object tracking in autonomous driving is a non‐linear *** better address the tracking problem,this paper leveraged an unscented Kalman filter to predict the object's *** the association stage,the Mahalanobis distance was employed as an affinity metric,and a Non‐minimum Suppression method was designed for *** the detections fed into the tracker and continuous‘predicting‐matching’steps,the states of each object at different time steps were described as their own continuous *** conducted extensive experiments to evaluate tracking accuracy on three challenging datasets(KITTI,nuScenes and Waymo).The experimental results demon-strated that our method effectively achieved multi‐object tracking with satisfactory ac-curacy and real‐time efficiency.

关键词： autonomous vehicle transportation

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：