检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Kun Lu, Jun Heilongjiang University College of Computer Science and Technology Harbin150080 China Jiaxiang Industrial Technology Research Institute of Hlju Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781728163277

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

YOLO-SOD: Improved YOLO Small Object Detection 21st

YOLO-SOD: Improved YOLO Small Object Detection

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Xu, Yang Lu, Jun Wang, Chao College of Computer Science and Technology Heilongjiang University Harbin150080 China Jiaxiang Industrial Technology Research Institute of Heilongjiang University Shandong Province Jining272400 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Heilongjiang University Harbin150080 China Wuhan University Hubei Province Wuhan430072 China

ISBN: (纸本)9789819601240

Small object detection has important application value in the fields of environmental monitoring, resource detection and analysis, etc. However, the current general object detectors are not very ideal for the detection of small objects. To this end, this paper proposes an efficient, low-complexity, anchor-free small object detection framework YOLO-SOD based on YOLOv8. First, a content-aware feature recombination upsampling operator (CARAFE) is integrated in the upsampling operation part of the framework to achieve more accurate and efficient feature reconstruction. Then, the spatial and channel reconstruction convolutional block (SCConv) is widely integrated in BackBone and Neck to reduce the computational cost caused by redundant feature extraction in visual tasks. Finally, the occlusion-aware attention module (SEAM) is introduced at the end of the detection framework to help the model more accurately identify occluded objects. The ablation experiment on the general small object detection dataset VisDrone2021 proves the effectiveness of several modules introduced in this paper for small object detection. On the VisDrone2021 dataset, YOLO-SOD can achieve an accuracy of 31.1% AP50:95 and 52.3% AP50, which are 2.5% and 3.1% higher than the baseline model respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities 24

On the Effectiveness of Function-Level Vulnerability Detecto...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hong Kong Jin YinHu Laboratory Wuhan China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China University of Colorado Colorado Springs Department of Computer Science Colorado Springs Colorado United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798400702174

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Sequential Topic Selection Model with Latent Variable for Topic-Grounded Dialogue

Sequential Topic Selection Model with Latent Variable for To...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Wen, Xiaofei Wei, Wei Mao, Xian-Ling Cognitive Computing and Intelligent Information Processing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science and Technology Beijing Institute of Technology China

Recently, topic-grounded dialogue system has attracted significant attention due to its effectiveness in predicting the next topic to yield better responses via the historical context and given topic sequence. However, almost all existing topic prediction solutions focus on only the current conversation and corresponding topic sequence to predict the next conversation topic, without exploiting other topic-guided conversations which may contain relevant topic-transitions to current conversation. To address the problem, in this paper we propose a novel approach, named Sequential Global Topic Attention (SGTA) to exploit topic transition over all conversations in a subtle way for better modeling post-to-response topic-transition and guiding the response generation to the current conversation. Specifically, we introduce a latent space modeled as a Multivariate Skew-Normal distribution with hybrid kernel functions to flexibly integrate the global-level information with sequence-level information, and predict the topic based on the distribution sampling results. We also leverage a topic-aware prior-posterior approach for secondary selection of predicted topics, which is utilized to optimize the response generation task. Extensive experiments demonstrate that our model outperforms competitive baselines on prediction and generation tasks. © 2022 Association for Computational Linguistics.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Simulation of Nuclear Reactor Accident Scenarios using Physics-Informed Neural Networks and Transfer-Learning 4

Simulation of Nuclear Reactor Accident Scenarios using Physi...

引用

4th International Conference on Electronic Information Engineering and Computer science, EIECS 2024

作者： Yu, Yang Xie, Yufei Wang, Wenlin Wu, Guohua Lan, Haitao Lin, Enbo An, Ping Sun, Zibin Zhang, Haichuan Wu, Yixian National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing Changsha China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China School of Automation Wuhan University of Technology Wuhan China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China Institute of Automotive Engineers Hubei University of Automotive Technology Shiyan China Nuclear Power Institute of China Chengdu China

ISBN: (纸本)9798331531409

In a Loss of Coolant Accident (LOCA), reactor core temperatures can rise rapidly, leading to potential fuel damage and radioactive material release. This research presents a groundbreaking method that combines the power of Monte Carlo Sampling and Physics-Informed Neural Networks (PINNs) to simulate and effectively address the challenging Loss of Coolant Accidents (LOCA) in nuclear reactors. In the event of a LOCA, reactor core temperatures can soar rapidly, posing a significant threat to fuel integrity and potentially leading to the release of radioactive materials. By leveraging the strengths of both Monte Carlo Sampling and PINNs, this approach aims to provide a comprehensive and accurate simulation framework for assessing and mitigating the consequences of such accidents. The method yields high prediction accuracy (MAE: 0.033, RMSE: 0.098, R2: 0.814) and demonstrates robustness through transfer learning, maintaining strong performance (MAE: 0.064, RMSE: 0.163, R2: 0.735). © 2024 IEEE.

关键词： Coolants

来源：评论

学校读者我要写书评

暂无评论

Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers

arXiv

引用

arXiv 2024年

作者： Chen, Jinsong Liu, Hanpeng Hopcroft, John E. He, Kun School of Computer Science and Technology Huazhong University of Science and Technology China Institute of Artificial Intelligence Huazhong University of Science and Technology China Hopcroft Center on Computing Science Huazhong University of Science and Technology China Department of Computer Science Cornell University United States

While tokenized graph Transformers have demonstrated strong performance in node classification tasks, their reliance on a limited subset of nodes with high similarity scores for constructing token sequences overlooks valuable information from other nodes, hindering their ability to fully harness graph information for learning optimal node representations. To address this limitation, we propose a novel graph Transformer called GCFormer. Unlike previous approaches, GCFormer develops a hybrid token generator to create two types of token sequences, positive and negative, to capture diverse graph information. And a tailored Transformer-based backbone is adopted to learn meaningful node representations from these generated token sequences. Additionally, GCFormer introduces contrastive learning to extract valuable information from both positive and negative token sequences, enhancing the quality of learned node representations. Extensive experimental results across various datasets, including homophily and heterophily graphs, demonstrate the superiority of GCFormer in node classification, when compared to representative graph neural networks (GNNs) and graph Transformers. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Effective Point Cloud Classification Method Based on Improved Non-local Neural Networks 25

An Effective Point Cloud Classification Method Based on Impr...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Song, Yanan Liu, Xianfei Shen, Weiming Gao, Yiping Zhou, Xianke Lu, Peng College of Computer Science and Technology Zhejiang University Institute of Computing Innovation Hangzhou China Zhejiang University Institute of Computing Innovation Hangzhou China State Key Lab. of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665405270

Deep learning is an important method to deal with point cloud, but its ability is limited to extract local features of point cloud. Many deep learning networks are designed to capture the local information, but they ignore the importance of non-local features to the point cloud. This paper proposes an improved non-local neural networks for point cloud classification. The non-local module can extract local and non-local features of the point cloud simultaneously. The local information is obtained based on the feature distance between neighborhood points searched by k-nearest neighbor method. The extracted local features are integrated into the non-local network, which can capture non-local features from the entire point cloud. The designed non-local module can be easily inserted into the existing point cloud processing network. The proposed method is evaluated on well-known ModelNet40 shape classification benchmark. Experimental results show that the proposed method achieves a significant improvement in classification accuracy. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs

arXiv

引用

arXiv 2023年

作者： Chen, Jinsong Liu, Chang Gao, Kaiyuan Li, Gaichao He, Kun Institute of Artificial Intelligence Huazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan430074 China

Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token module. For each node, Hop2Token aggregates the neighborhood features from different hops into different representations, producing a sequence of token vectors as one input. In this way, NAGphormer could be trained in a mini-batch manner and thus could scale to large graphs. Moreover, we mathematically show that compared to a category of advanced Graph Neural Networks (GNNs), called decoupled Graph Convolutional Networks, NAGphormer could learn more informative node representations from multi-hop neighborhoods. In addition, we propose a new data augmentation method called Neighborhood Augmentation (NrAug) based on the output of Hop2Token that augments simultaneously the features of neighborhoods from global as well as local views to strengthen the training effect of NAGphormer. Extensive experiments on benchmark datasets from small to large demonstrate the superiority of NAGphormer against existing graph Transformers and mainstream GNNs, and the effectiveness of NrAug for further boosting NAGphormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Knowledge Distillation for Tiny Defect Detection 25

Semi-supervised Knowledge Distillation for Tiny Defect Detec...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Cao, Yunkang Song, Yanan Xu, Xiaohao Li, Shuya Yu, Yuhao Zhang, Yifeng Shen, Weiming Huazhong University of Science and Technology School of Mechanical Science and Engineering Wuhan430074 China Zhejiang University Institute of Computing Innovation Hangzhou311215 China

ISBN: (纸本)9781665405270

Image anomaly detection can automatically detect defects using images of products, which is crucial for product quality controls. Because of insufficient abnormal data, unsupervised image anomaly detection based on knowledge distillation has attracted broad attention recently. However, fully unsupervised methods suffer from detecting tiny anomalies that widely exist in industrial products because the features of tiny anomalies and normal features extracted by the teacher network are similar. This paper extends current unsupervised anomaly detection methods into a semi-supervised manner, simultaneously leveraging normal data and a limited amount of abnormal data. An automobile plastic parts dataset is established to prove the effectiveness of the proposed method. Experiments show that the proposed method can accurately detect small anomalies and largely surpass a powerful baseline (6% in AU-ROC, 10% in F1-score, 11% in Accuracy). © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Fourth-order multiple-relaxation-time lattice Boltzmann model and equivalent finite-difference scheme for one-dimensional convection-diffusion equations

引用

Physical Review E 2023年第5期107卷 055305-055305页

作者： Ying Chen Zhenhua Chai Baochang Shi School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan 430074 China Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology Wuhan 430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan 430074 China

In this paper, we first develop a fourth-order multiple-relaxation-time lattice Boltzmann (MRT-LB) model for the one-dimensional convection-diffusion equation (CDE) with the constant velocity and diffusion coefficient, where the D1Q3 (three discrete velocities in one-dimensional space) lattice structure is used. We also perform the Chapman-Enskog analysis to recover the CDE from the MRT-LB model. Then an explicit four-level finite-difference (FLFD) scheme is derived from the developed MRT-LB model for the CDE. Through the Taylor expansion, the truncation error of the FLFD scheme is obtained, and at the diffusive scaling, the FLFD scheme can achieve the fourth-order accuracy in space. After that, we present a stability analysis and derive the same stability condition for the MRT-LB model and FLFD scheme. Finally, we perform some numerical experiments to test the MRT-LB model and FLFD scheme, and the numerical results show that they have a fourth-order convergence rate in space, which is consistent with our theoretical analysis.

关键词： Lattice-Boltzmann methods

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：