检索结果-内蒙古大学图书馆

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Shi, Yan Wang, Guoyin Liu, Qun Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing Chongqing China

ISBN: (纸本)9798350330076

The majority of object detection methods typically depend on a significant quantity of annotated data, while few-shot object detection (FSOD) endeavors to identify novel classes of objects using a limited number of training instances. However, the limited number of samples leads to the problem of disparate data distributions between the source and target domains, which makes the generalization ability of the detector usually weak. In this paper, we combine data augmentation with fine-tuning to design a pseudo-labeled constrained model called LCDA, aiming to obtain high-quality pseudo-labels to effectively enrich the training examples. Furthermore, we leverage the pre-trained CLIP model to enhance the quality of pseudo-labels by restricting the category information as well as the designed bounding box consistency criterion. The experimental outcomes demonstrate that our model outperforms the existing models on two public datasets across various shot scenarios. The average enhancement of our method on different shots is 1.2AP, 1.6AP, 2.3AP, 2.7AP, and 4.2AP. We also validate the performance of the model in real applications of the USV dataset which shows an improvement of 1.9AP over the baseline methods. All demonstrate the effectiveness of our model. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligence Research:From Bio-inspired Single-population Swarm Intelligence to Human-machine Hybrid Swarm Intelligence

引用

Machine Intelligence Research 2023年第1期20卷 121-144页

作者： Guo-Yin Wang Dong-Dong Cheng De-You Xia Hai-Huan Jiang Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Big Data and Intelligent Engineering Yangtze Normal UniversityChongqing 408100China

Swarm intelligence has become a hot research field of artificial *** the importance of swarm intelli-gence for the future development of artificial intelligence,we discuss and analyze swarm intelligence from a broader and deeper *** a broader sense,we are talking about not only bio-inspired swarm intelligence,but also human-machine hybrid swarm *** a deeper sense,we discuss the research using a three-layer hierarchy:in the first layer,we divide the research of swarm intelli-gence into bio-inspired swarm intelligence and human-machine hybrid swarm intelligence;in the second layer,the bio-inspired swarm intelligence is divided into single-population swarm intelligence and multi-population swarm intelligence;and in the third layer,we re-view single-population,multi-population and human-machine hybrid models from different ***-population swarm intel-ligence is inspired by biological *** further solve complex optimization problems,researchers have made preliminary explor-ations in multi-population swarm ***,it is difficult for bio-inspired swarm intelligence to realize dynamic cognitive in-telligent behavior that meets the needs of human *** have introduced human intelligence into computing systems and proposed human-machine hybrid swarm *** addition to single-population swarm intelligence,we thoroughly review multi-population and human-machine hybrid swarm intelligence in this *** also discuss the applications of swarm intelligence in optimization,big data analysis,unmanned systems and other ***,we discuss future research directions and key issues to be studied in swarm intelligence.

关键词： Swarm intelligence single-population multi-population human-machine hybrid multi-granularity

来源：评论

学校读者我要写书评

暂无评论

Improved Self-Attention for Spodoptera Frugiperda Larval Instar Stages Identification 7

Improved Self-Attention for Spodoptera Frugiperda Larval Ins...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Wang, Mingyang Lu, Ying Xu, Quanyuan College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Big Data State Forestry Administration on Southwest Forestry University Key Laboratory of Forestry and Ecological Kunming China

ISBN: (纸本)9798350350890

Spodoptera frugiperda (fall armyworm, FAW) is a pest that poses a significant threat to global agriculture, with its larvae exhibiting unique morphological characteristics and varying degrees of harm at different instar stages. This study proposes a method that incorporates an improved self-attention mechanism to achieve rapid and accurate identification of FAW larval instars. This method can be seamlessly integrated into convolutional neural networks (CNNs), enhancing recognition performance by focusing on the global features of images. Furthermore, this research has constructed an image dataset of FAW larvae at various developmental stages under field and laboratory conditions to validate the effectiveness of the proposed method. Experimental results demonstrate that our method improves the recognition accuracy across various CNN architectures, achieving accuracy enhancements of 5.49%, 7.38%, 5.79%, and 5.59% on Alexnet, vgg16, resnet50, and resnet101, respectively. Our approach provides technicians with a convenient, intelligent, and precise tool to identify FAW larval instar stages. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 236-248页

作者： Zhen-Hong Shang Long Chen Zhen-Ping Qiang Yi Bi Run-Xin Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Observatories Chinese Academy of Sciences

Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar *** paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar *** proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow ***,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow *** apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar *** experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index ***,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity *** code is available at https://***/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.

关键词： methods: data analysis Sun: fundamental parameters techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch Attention Transformer for Visual Commonsense Reasoning 6

Dual-Branch Attention Transformer for Visual Commonsense Rea...

引用

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Ma, Xuerui Bai, Zongwen Zhou, Meili Gao, Yiqun School of Physics and Electronic Information Yan'an University Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an China

ISBN: (纸本)9798331541750

Visual Commonsense Reasoning (VCR) is a challenging task that requires a model to select the correct answer in the context of a given image and question, while also providing a reasonable explanation to justify the chosen answer. In this paper, we propose a novel dual-branch attention network model that effectively models dense intra-modal and inter-modal interactions. Our model utilizes a self-attention mechanism to attend to visual and textual information independently, while employing a bidirectional guided attention mechanism to facilitate effective interaction between different modalities, thus correlating visual information with textual information. By stacking multiple dual-branch attention modules (DBAs), our model is capable of deeply exploring data features and extracting more powerful and informative prior features. By achieving a common focus on visual and textual information, we enhance the subtlety of our understanding and significantly improve our ability to perform visual reasoning. Our comprehensive and qualitative assessments on the public VCR dataset illustrate that our methodology surpasses most models, providing a new solution for Visual Commonsense Reasoning tasks. © 2024 IEEE.

关键词： dual-branch attention multimodel Visual Commonsense Reasoning

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: Accelerating Distributed GNN Training Leveraging Feature-Centric Model Migration 23

LeapGNN: Accelerating Distributed GNN Training Leveraging Fe...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Chen, Weijian He, Shuibing Qu, Haoyang Zhang, Xuechen The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3 © 2025 FAST. 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

keypoint-based Progressive Chain-of-Thought Distillation for LLMs 41

Keypoint-based Progressive Chain-of-Thought Distillation for...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Feng, Kaituo Li, Changsheng Zhang, Xiaolu Zhou, Jun Yuan, Ye Wang, Guoren Beijing Institute of Technology China Ant Group China Hebei Province Key Laboratory of Big Data Science and Intelligent Technology China

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin. Copyright 2024 by the author(s)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

SDGNN: Symmetry-Preserving Dual-Stream Graph Neural Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1717-1719页

作者： Jiufang Chen Ye Yuan Xin Luo the College of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China the College of Computer and Information Science Southwest UniversityChongqing 400715China IEEE

Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.

关键词： representation preserving undirected

来源：评论

学校读者我要写书评

暂无评论

Improving Cross-Domain Named Entity Recognition from the Perspective of Representation 28th

Improving Cross-Domain Named Entity Recognition from the P...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Xu, Jingyun Cai, Yi School of Software Engineering South China University of Technology Guangzhou510650 China The Key Laboratory of Big Data and Intelligent Robots South China University of Technology and the Pazhou Lab Guangzhou510335 China

ISBN: (纸本)9783031306778

Recently, cross-domain named entity recognition (cross-domain NER), which can reduce the high data annotation costs faced by fully-supervised methods, has drawn attention. Most competitive approaches mainly rely on pre-trained language models like BERT to represent words. As such, the original chaotic representations may bring challenges (e.g., entity span detection errors and entity type misclassification) for them. Motivated by this, this proposal proposes to improve cross-domain NER by refining the original representations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Contrastive Learning Cross-domain Named Entity Recognition Representation

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：