检索结果-内蒙古大学图书馆

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1899-1912页

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Drug-Protein Interaction Prediction by Fusion of Attention and Graph Neural Network 42

Drug-Protein Interaction Prediction by Fusion of Attention a...

引用

42nd Chinese Control Conference, CCC 2023

作者： Chen, Tianrui Tuo, Shouheng Feng, Zengyu School of Computer Science and Technology Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9789887581543

The identification of drug-protein interactions (DTIs) is a critical step in drug development and repositioning. However, detecting these interactions using scientific methods presents a formidable challenge. Existing models often struggle to extract relevant information from drug-protein sequences, and they fail to consider pre-existing interactions between pairs. Here, we introduce a deep learning model, DPAG, based on attention mechanisms and graph neural networks, which overcomes these limitations. DPAG leverages information from both the drug and protein sequences, as well as the association between drug-protein pairs, to predict DTIs. We conducted multiple experiments to evaluate the performance of the model in benchmark datasets, and the results showed that DPAG achieved excellent performance in terms of AUC, AUPR, precision, and recall. Our findings suggest that DPAG holds significant potential as a promising tool for predicting DTIs in drug development and repositioning. Code is available at https://***/veresse/DPAG. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Mixture of experts for audio-visual learning 24

Mixture of experts for audio-visual learning

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Ying Cheng Yang Li Junjie He Rui Feng School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing and Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

With the rapid development of multimedia technology, audio-visual learning has emerged as a promising research topic within the field of multimodal analysis. In this paper, we explore parameter-efficient transfer learning for audio-visual learning and propose the Audio-Visual Mixture of Experts (AVMoE) to inject adapters into pre-trained models flexibly. Specifically, we introduce unimodal and cross-modal adapters as multiple experts to specialize in intra-modal and intermodal information, respectively, and employ a lightweight router to dynamically allocate the weights of each expert according to the specific demands of each task. Extensive experiments demonstrate that our proposed approach AVMoE achieves superior performance across multiple audio-visual tasks, including AVE, AVVP, AVS, and AVQA. Furthermore, visual-only experimental results also indicate that our approach can tackle challenging scenes where modality information is missing. The source code is available at https://***/yingchengy/AVMOE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Universal RNA Dual-Terminal Labeling Method for Sensing RNA-Ligand Interactions

引用

CCS Chemistry 2023年第1期5卷 221-233页

作者： Longhuai Cheng Dejun Ma Jie Zhang Xueying Kang Yang Wu Yi Zhao Long Yi Zhen Xi State Key Laboratory of Elemento-Organic Chemistry Department of Chemical BiologyCollege of ChemistryNational Pesticide Engineering Research CenterCollaborative Innovation Center of Chemical Science and EngineeringNankai UniversityTianjin 300071 State Key Laboratory of Organic-Inorganic Composites and Beijing Key Laboratory of Bioprocess Beijing University of Chemical Technology(BUCT)Beijing 100029 Key Laboratory of Intelligent Information Processing Research Center for Ubiquitous Computing SystemsInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190

Dual labeling of an RNA can provide Förster resonance energy transfer(FRET)sensors for studying RNA folding,miRNA maturation,and RNA-protein ***,we report the development of a highly efficient strategy for direct dual-terminal labeling of any RNA of *** explored new Michael cycloaddition for facile labeling of 5′-terminal RNA with improved *** chemical tetrazinylation of RNA at the 3′-terminus was achieved with the highly efficient and catalysis-free tetrazine-cycloalkyne *** single-terminal labeling methods were combined for dual-terminal labeling of an RNA including short hairpin RNA,pre-miRNA,riboswitch,and noncoding ***,these dual-labeled RNA-based FRET sensors were used to monitor RNA-ligand interactions in vitro and in live *** is anticipated that these universal RNA labeling strategies will be useful to study RNA structures and functions.

关键词： dual labeling Förster resonance energy transfer sensor Michael cycloaddition tetrazinecycloalkyne ligation RNA-ligand interaction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme for Marine Diesel Engines 11

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme ...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： Zhong, Kai Wang, Jiayi Pan, Donghui Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Anhui Hefei230601 China School of Mathematical Science Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Hefei230601 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Since the marine diesel engine is one of the most popular power equipments for modern shipping, accurate and timely diagnose the faults occurred in diesel engine is extraordinary important for long service life and high reliability. Note that Fisher discriminant analysis (FDA) has been widely applied in fault diagnosis field. However, it is quite susceptible to the small sample size (SSS) problem, which is very common in the running process of diesel engine. In response to the problem, this study pro-poses a new fault classification criterion based exponential discriminant analysis (EDA) scheme for diesel engine fault diagnosis, in which the exponential transformation is carried out first to enlarge the margin between different classes, thus the different fault classes are further separated and the diagnosis capability is enhanced. In addition, the theorems of matrix exponential guarantee that the matrix exp (Sw) is always full-rank, even though the Sw is singular. That means, the novel methodology is still appli-cable when confronts with the SSS problem. Finally, based on the more reasonable fault classification criterion, the simulation results on a real-world two-stroke six-cylinder low-speed marine diesel engine indicate that the EDA based diagnosis scheme achieves higher fault diagnosis accuracy with good robustness and practicability in real-world engineering applications. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Leveraging catastrophic forgetting to develop safe diffusion models against malicious finetuning 24

Leveraging catastrophic forgetting to develop safe diffusion...

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Jiadong Pan Hongcheng Gao Zongyu Wu Taihang Hu Li Su Qingming Huang Liang Li Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS and University of Chinese Academy of Sciences University of Chinese Academy of Sciences The Pennsylvania State University Nankai University Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS

ISBN: (纸本)9798331314385

Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful images but such external filters do not inherently detoxify the model and can be easily bypassed. Hence, model unlearning and data cleaning are the most essential methods for maintaining the safety of models, given their impact on model parameters. However, malicious fine-tuning can still make models prone to generating harmful or undesirable images even with these methods. Inspired by the phenomenon of catastrophic forgetting, we propose a training policy using contrastive learning to increase the latent space distance between clean and harmful data distribution, thereby protecting models from being fine-tuned to generate harmful images due to forgetting. The experimental results demonstrate that our methods not only maintain clean image generation capabilities before malicious fine-tuning but also effectively prevent DMs from producing harmful images after malicious fine-tuning. Our method can also be combined with other safety methods to maintain their safety against malicious fine-tuning further.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-notch Ultra-wideband Bandpass Filter Based On Folded Dual-mode Resonator

Dual-notch Ultra-wideband Bandpass Filter Based On Folded Du...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Li, Qingqing Wu, Xianliang Huang, Zhixiang Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665452366

Aiming at the problem that ultra-wideband systems are easily interfered by narrowband signals, In this paper, a novel ultra-wideband (UWB) bandpass filter with dual-notch characteristics. This filter is mainly composed of Composition of a multimode resonator (MMR)and a folded dual-mode step-impedance resonator. Paralleling T-shaped SIR stubs in the basic MMR structure realizes the introduction of transmission zeros within the passband. At the same time, a pair of high-impedance stubs are also loaded to extend the upper stopband of the filter, and a folded dual-mode stepped impedance resonator is coupled below the filter to generate dual-notch frequencies. Through the electromagnetic simulation software HFSS for simulation optimization, the simulation results show that the passband of the filter is 3.4211.21GHz and its notch frequencies are 8.8GHz and 9.5GHz respectively. Insertion loss below 0.5dB and stopband up to 20GHz (S21 © 2022 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

Video Rumor Classification Based on Multi-modal Theme and keyframe Fusion 17th

Video Rumor Classification Based on Multi-modal Theme and ...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： You, Jinpeng Lin, Yanghao Lin, Dazhen Cao, Donglin Artificial Intelligence Department Xiamen University Xiamen361005 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China

ISBN: (纸本)9789819923557

In recent years, short video platforms have become the main source of online rumors. According to the statistics of Shanghai online rumor refutation platform in 2021, the number of short video rumors was about five times that of short video rumors in 2020, which makes it necessary to detect rumors of short videos. At present, short video rumor detection has the problem of multi-modal information fusion, the traditional multi-modal fusion uses deep learning to obtain the underlying features of multi-modality and then aggregate them into cross-modal features. However, there are distortions of theme and tampering with key-frame in rumor videos. Therefore, short video rumors need to learn features from the perspective of theme and key-frame. Aiming at the problem of multi-modal information fusion of short video rumors, this paper proposes a short video rumor detection model (TKCM) based on theme and key-frame. It uses aggregation network to obtain the theme feature of video, attention network to obtain the key-frame feature, and fuses multi-modality by modal adjustment mechanism for short video rumor detection. Experimental results show that the F1 score of the proposed method on the short video rumor dataset is improved by 2%–5% compared with some state-of-the-art video classification models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

αSetup-PCTL:An Adaptive Setup-Based Two-Level Preconditioner for Sequence of Linear Systems of Three-Temperature Energy Equations

引用

Communications in Computational Physics 2022年第10期32卷 1287-1309页

作者： Silu Huang Xiaoqiang Yue Xiaowen Xu Laboratory of Computational Physics Institute of Applied Physics and ComputationalMathematicsBeijing 100088China National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing and Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China

The iterative solution of the sequence of linear systems arising from threetemperature(3-T)energy equations is an essential component in the numerical simulation of radiative hydrodynamic(RHD)***,due to the complicated application features of the RHD problems,solving 3-T linear systems with classical preconditioned iterative techniques is *** address this difficulty,a physicalvariable based coarsening two-level(PCTL)preconditioner has been proposed by dividing the fully coupled system into four individual easier-to-solve *** its nearly optimal complexity and robustness,the PCTL algorithm suffers from poor efficiency because of the overhead associatedwith the construction of setup phase and the solution of ***,the PCTL algorithm employs a fixed strategy for solving the sequence of 3-T linear systems,which completely ignores the dynamically and slowly changing features of these linear *** address these problems and to efficiently solve the sequence of 3-T linear systems,we propose an adaptive two-level preconditioner based on the PCTL algorithm,referred to as α*** adaptive strategies of the αSetup-PCTL algorithm are inspired by those of αSetup-AMG algorithm,which is an adaptive-setup-based AMG solver for sequence of sparse linear *** proposed αSetup-PCTL algorithm could adaptively employ the appropriate strategies for each linear system,and thus increase the overall *** results demonstrate that,for 36 linear systems,the αSetup-PCTL algorithm achieves an average speedup of 2.2,and a maximum speedup of 4.2 when compared to the PCTL algorithm.

关键词： Sequence of linear systems sparse linear solver preconditioning methods radiation hydrodynamics simulation

来源：评论

学校读者我要写书评

暂无评论

Sparsity-aware Subband Adaptive Filtering in Impulsive Interferences 7

Sparsity-aware Subband Adaptive Filtering in Impulsive Inter...

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Gong, Zhikai Li, Yingsong Pang, Baohe Li, Xueyan Xiao, Wudang Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing China Innopolis University Faculty of Computer and Engineering Sciences Russia

ISBN: (纸本)9798350384437

In this paper, we propose two new subband adaptive filtering (SAF) algorithms based on the cost function of the logistic distance metric cost function and use the proportionate proximal gradient algorithm to exploit the sparsity of the system fully. Compared with prior works, the proposed algorithms can handle many different situations better. Through computer simulations, we prove that the algorithm performs excellently in sparse systems disturbed by impulse noises. The algorithm can be used in areas like system identifications. © 2024 IEEE.

关键词： Adaptive filtering

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：