检索结果-内蒙古大学图书馆

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lu, Zhiguang Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

Improving Multi-Label Contrastive Learning by Leveraging Label Distribution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Ning Lyu, Shen-Huan Wu, Tian-Shuang Wang, Yanyan Tang, Bin Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and negative samples based on the overlap between labels and used them for label-wise loss balancing. However, these methods suffer from a complex selection process and fail to account for the varying importance of different labels. To address these problems, we propose a novel method that improves multi-label contrastive learning through label distribution. Specifically, when selecting positive and negative samples, we only need to consider whether there is an intersection between labels. To model the relationships between labels, we introduce two methods to recover label distributions from logical labels, based on Radial Basis Function (RBF) and contrastive loss, respectively. We evaluate our method on nine widely used multi-label datasets, including image and vector datasets. The results demonstrate that our method outperforms state-of-the-art methods in six evaluation metrics. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

Research on patent recommendation method based on graph neural network 26

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neur...

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Enchao Liu, Weidong Liu, Shi Cao, Yan Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350331684

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation. © 2023 IEEE.

关键词： Patents and inventions

Variation in the life history strategy underlies functional diversity of tumors

学校读者我要写书评

暂无评论

National Science Review 2021年第2期8卷 32-42页

作者： Tao Li Jialin Liu Jing Feng Zhenzhen Liu Sixue Liu Minjie Zhang Yuezheng Zhang Yali Hou Dafei Wu Chunyan Li Yongbin Chen Hua Chen Xuemei Lu State Key Laboratory of Genetic Resources and Evolution Kunming Institute of ZoologyChinese Academy of Sciences CAS Key Laboratory of Genomic and Precision Medicine Beijing Institute of GenomicsChinese Academy of Sciences Center for Excellence in Animal Evolution and Genetics Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine and Engineering and Key Laboratory of Big Data-Based Precision Medicine(Ministry of Industry and Information Technology)Beihang University Key Laboratory of Animal Models and Human Disease Mechanisms of the Chinese Academy of Sciences and Yunnan Province Kunming Institute of Zoology

Classical r-vs. K-selection theory describes the trade-offs between high reproductive output and competitiveness and guides research in evolutionary ecology. While its impact has waned in the recent past,cancer evolution may rekindle it. Herein, we impose r-or K-selection on cancer cell lines to obtain strongly proliferative r cells and highly competitive K cells to test ideas on life-history strategy evolution. RNA-seq indicates that the trade-offs are associated with distinct expression of genes involved in the cell cycle,adhesion, apoptosis, and contact inhibition. Both empirical observations and simulations based on an ecological competition model show that the trade-off between cell proliferation and competitiveness can evolve adaptively. When the r and K cells are mixed, they exhibit strikingly different spatial and temporal distributions. Due to this niche separation, the fitness of the entire tumor increases. The contrasting selective pressure may operate in a realistic ecological setting of actual tumors.

关键词： density-dependent selection trade-offs cancer cell phenotypic diversity competition

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Chun Yang, Longwei Dong, Dongmei Li, Zheng Yang, Wei Han, Zhigang Wang, Jiayao School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan Engineering Laboratory of Spatial Information Processing Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China Beijing Electro-Mechanical Engineering Institute Beijing100074 China College of Geography and Environmental Science Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches centering around each pixel are often used for classification. However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify. These boundary patchs are mixed with multi-class spectral information. Inspired by this, we propose to augment the prototype network with TransMix for few-shot hyperspectrial image classification(APNT). While taking the prototype network as the backbone, it adopts the transformer as feature extractor to learn the pixel-to-pixel relation and pay different attentions to different pixels. At the same time, instead of directly using the patches which are cut from the hyperspectral images for training, it randomly mixs up two patches to imitate the boundary patches and uses the synthetic patches to train the model, with the aim to enlarge the number of hard training samples and enhance their diversity. And by following the data agumentation technique TransMix, the attention returned by the transformer is also used to mix up the labels of two patches to generate better labels for synthetic patches. Compared with existing methods, the proposed method has demonstrated sate of the art performance and better robustness for few-shot hyperspectral image classification in our experiments. All the codes are available at https://***/HENULWY/APNT. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

TrustUQA: A Trustful Framework for Unified Structured data Question Answering

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Wen Jin, Long Zhu, Yushan Chen, Jiaoyan Huang, Zhiwei Wang, Junjie Hua, Yin Liang, Lei Chen, Huajun Zhejiang University China University of Manchester United Kingdom Ant Group China ZJU-Ant Group Joint Lab of Knowledge Graph China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions include question to formal query parsing and retrieval-based answer generation. However, current methods of the former often suffer from weak generalization, failing to dealing with multi-types of sources, while the later is limited in trustfulness. In this paper, we propose TrustUQA, a trustful QA framework that can simultaneously support multiple types of structured data in a unified way. To this end, it adopts an LLM-friendly and unified knowledge representation method called Condition Graph (CG), and uses an LLM and demonstration-based two-level method for CG querying. For enhancement, it is also equipped with dynamic demonstration retrieval. We have evaluated TrustUQA with 5 benchmarks covering 3 types of structured data. It outperforms 2 existing unified structured data QA methods. In comparison with the baselines that are specific to one data type, it achieves state-of-the-art on 2 of the datasets. Further more, we have demonstrated the potential of our method for more general QA tasks, QA over mixed structured data and QA across structured data. The code is available at https://***/zjukg/TrustUQA. Copyright © 2024, The Authors. All rights reserved.

关键词： Structured Query Language

A Dual-Notch Ultra-Wideband Filter with High Selectivity and Miniaturization Based on Open Stubs

学校读者我要写书评

暂无评论

A Dual-Notch Ultra-Wideband Filter with High Selectivity and...

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Ya He Mingming Gao CongYing Wang Yan He ZhenZhi Yang WenXin Yang College of Electronics and Information Engineering Liaoning Technicial University Huludao Liaoning Province China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

This manuscript introduces the design of an ultra-wideband (UWB) microstrip line filter implemented through a novel multimode resonator comprising open-circuited stubs. The multimode resonator has three open-circuited stubs, two short lines, and a high-impedance microstrip line. The filter demonstrates a 3dB bandwidth ranging from 3.72 to 11.23 GHz, centered at 7.48 GHz. Asymmetric coupling techniques and split-ring resonators on both sides of the multimode resonator introduce notches at 8.62-8.73 GHz and 9.21-9.64 GHz. The UWB filter designed in this study exhibits a low insertion loss of merely 0.51 dB. The notches demonstrate remarkable attenuation, achieving 29.90 dB and 24.31 dB, respectively, highlighting superior notch suppression performance. Additionally, the filter's compact structure fulfills miniaturization requirements, possessing a size of only 0.61*0.20 $(\lambda_{g}*\lambda_{g})$ .

关键词： Couplings Microstrip filters Microwave technology Microstrip resonators Resonator filters Millimeter wave technology Resonant frequency

Embedding VLAD in Transformer for Video Question Answering

学校读者我要写书评

暂无评论

Jisuanji Xuebao/Chinese Journal of Computers 2023年第4期46卷 671-689页

作者： Guo, Dan Yao, Shen-Tao Wang, Hui Wang, Meng School of Computer and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230094 China Key Laboratory of Knowledge Engineering with Big Data（Hefei University of Technology） Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province（Hefei University of Technology） Hefei230601 China

Video question answering（VideoQA）is a typical cross-modal understanding task. Its challenge lies in how to learn appropriate multimodal representation and cross-modal correlation for answer inference. Most existing video question answering methods focus on the latter，e. g.，relationship learning between each video frame or clip and word. In this work， we devote to advanced feature embedding of both video and query. We develop a clustering-based VLAD technique for VideoQA. The novelty of our work is the joint exploitation of temporal aggregation and correlation in multimodality. We propose an end-to-end trainable Transformed VLAD embedding network， named TVLAD-Net. TVLAD-Net constructs a differentiable aggregation network module（i. e.， convolutional Residual-less VLAD Block）to generate compact VLAD descriptors（transforming N frames，clips or words to compact K descriptors while K © 2023 Science Press. All rights reserved.

关键词： Semantics

data Processing Technology for Network Abnormal Traffic Detection 4

学校读者我要写书评

暂无评论

Data Processing Technology for Network Abnormal Traffic Dete...

4th International Conference on Machine Learning and big data Analytics for IoT Security and Privacy, SPIoT 2023

作者： Wang, Kun Fu, Yu Duan, Xueyuan Xu, Jianqiao Liu, Taotao Department of Information Security Naval University of Engineering Wuhan430033 China School of Mathematics and Information Engineering Xinyang Vocational and Technical College Xinyang464000 China College of Computer and Information Technology Xinyang Normal University Xinyang464000 China Henan Key Laboratory of Analysis and Applications of Education Big Data Xinyang Normal University Xinyang464000 China

At present, the threats to network security are also increasing, among which abnormal traffic detection is the key link to ensure network security. Traditional detection methods based on signature or threshold are often difficult to adapt to the increasingly complex network environment and new attack methods. Therefore, this paper optimizes and improves the data processing technology, proposes a network ATD method based on particle swarm optimization(PSO) algorithm, and explores in detail the traffic data collection and pre-processing, the feature recognition of abnormal traffic, the application of PSO algorithm, real-time monitoring and response mechanism. The results of two sets of simulation experiments are as follows: compared with the traditional model, the accuracy rate of ATD of the improved algorithm is increased by 7.2% on average, and the detection time is reduced by 7.35s on average. This method not only enhances the adaptability of the model to new attacks, but also improves the degree of automation of detection. © 2024 The Authors.

关键词： Particle swarm optimization (PSO)