检索结果-内蒙古大学图书馆

FDBPL: Faster distillation-based prompt learning for region-aware vision-language models adaptation

Expert Systems with Applications 2025年 293卷

作者： Zherui Zhang Jiaxin Wu Changwei Wang Rongtao Xu Longzhao Huang Wenhao Xu Wenbo Xu Li Guo Shibiao Xu School of Artificial Intelligence Beijing University of Posts and Telecommunications Haidian China School of National Elite Institute of Engineering Chongqing University Chongqing China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely heavily on task-specific hard labels, limiting their generalization to unseen categories. Recent popular distillation-based prompt learning methods improve generalization by exploiting larger teacher VLMs and unsupervised knowledge transfer, yet their repetitive teacher model online inference sacrifices the inherent training efficiency advantage of prompt learning. In this paper, we propose F aster D istillation- B ased P rompt L earning ( FDBPL ), which addresses these issues by sharing soft supervision contexts across multiple training stages and implementing accelerated I/O. Furthermore, FDBPL introduces a region-aware prompt learning paradigm with dual positive-negative prompt spaces to fully exploit randomly cropped regions that containing multi-level information. We propose a positive-negative space mutual learning mechanism based on similarity-difference learning, enabling student CLIP models to recognize correct semantics while learning to reject weakly related concepts, thereby improving zero-shot performance. Unlike existing distillation-based prompt learning methods that sacrifice parameter efficiency for generalization, FDBPL maintains dual advantages of parameter efficiency and strong downstream generalization. Comprehensive evaluations across 11 datasets demonstrate superior performance in base-to-new generalization, cross-dataset transfer, and robustness tests, achieving 2.2 × faster training speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using NSGA-Ⅲ for optimising biomedical ontology alignment

引用

CAAI Transactions on Intelligence technology 2019年第3期4卷 135-141页

作者： Xingsi Xue Jiawei Lu Junfeng Chen College of Information Science and Engineering Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Intelligent Information Processing Research Center Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Fujian Key Laboratory for Automotive Electronics and Electric Drive Fujian University of TechnologyFuzhouFujianPeople’s Republic of China College of IOT Engineering Hohai UniversityChangzhouJiangsuPeople’s Republic of China

To support semantic inter-operability between the biomedical information systems, it is necessary to determine the correspondences between the heterogeneous biomedical concepts, which is commonly known as biomedical ontology matching. Biomedical concepts are usually complex and ambiguous, which makes matching biomedical ontologies a challenge. Since none of the similarity measures can distinguish the heterogeneous biomedical concepts in any context independently, usually several similarity measures are applied together to determine the biomedical concepts mappings. However, the ignorance of the effects brought about by different biomedical concept mapping’s preference on the similarity measures significantly reduces the alignment’s quality. In this study, a non-dominated sorting genetic algorithm (NSGA)-III-based biomedical ontology matching technique is proposed to effectively match the biomedical ontologies, which first utilises an ontology partitioning technique to transform the large-scale biomedical ontology matching problem into several ontology segment-matching problems, and then uses NSGA-III to determine the optimal alignment without tuning the aggregating weights. The experiment is conducted on the anatomy track and large biomedic ontologies track which are provided by the Ontology Alignment Evaluation Initiative (OAEI), and the comparisons with OAEI’s participants show the effectiveness of the authors’ approach.

关键词： ontology ontologies transform together Ontology complex context effects

来源：评论

学校读者我要写书评

暂无评论

How to fast verify collatz conjecture by automata 21

How to fast verify collatz conjecture by automata

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Ren, Wei Xiao, Ruiyang School of Computer Science China University of Geoseciences Wuhan430074 China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guizhou China

ISBN: (纸本)9781728120584

To verify Collatz conjecture for a given integer, we need to justify whether or not the given starting number goes to 1 finally. Current method computes 3∗x+1 and x/2 one by one. In this paper, we propose an automata-based algorithm to compute the process in a batch with m steps - (3∗x+1)2 or x/2. We also propose reduced Collatz conjecture and we prove it is equivalent to Collazt conjecture. We also point out that original dynamics is the combination of reduced dynamics. (Original dynamics is a serial of occurred 3∗x+1 and x/2 computation in the process from a starting number to 1;Reduced dynamics is a serial of occurred 3∗x+1 and x/2 computation in the process from a starting number to the first transformed number that is less than the starting number.) We study the properties of reduced dynamics and discover that reduced dynamics for some starting numbers can be determined directly without conducting concrete 3∗x+1 or x/2 computations. We build a binary tree called Collatz tree and use it as a visual tool for automata design. We find that each partition of starting number residue class decides the further computation is whether 3∗x+1 or x/2. The proposed automata can output code segment with m+2 computations in terms of (3∗x+1)/2 or x/2 by taking as input x=4t+3, where t is in residue class i module 2m and m is a natural number. We finally propose a conjecture whose proof implies the proof of Collatz conjecture by using proposed Collatz tree. © 2019 IEEE.

关键词： Number theory

来源：评论

学校读者我要写书评

暂无评论

Feature Enhanced Centernet for Object Detection in Remote Sensing Images

Feature Enhanced Centernet for Object Detection in Remote Se...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tong Zhang Guanqun Wang Yin Zhuang He Chen Hao Shi Liang Chen Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Multi-scale object detection in optical remote sensing imagery is a challenging task due to the varied object scales. Existed state-of-art object detection methods have achieved significant growth. However, most of the methods are based on default anchors, which need to be predefined. The multi-scale object detection accuracy still needs to be improved, especially for small and dense objects. To improve the robustness of the detection algorithm and the performance of multi-scale object detection, a novel anchor-free multi-scale object detection method Feature Enhanced CenterNet is proposed in this paper. First, we use the “encoder-decoder” structure and introduce horizontal connections to enhance feature representation capabilities. Second, an context-aware up-sampling method is proposed to obtain feature maps with suitable scale. To demonstrate the performance of the proposed method, we perform abundant experiments on the public remote sensing datasets. The experimental results demonstrate the robustness and effectiveness of the proposed method.

关键词： Object detection Feature extraction Detectors Robustness Optical imaging Convolution Semantics

来源：评论

学校读者我要写书评

暂无评论

Speckle tracking motion estimation based on shear wave imaging 2

Speckle tracking motion estimation based on shear wave imagi...

引用

2nd IEEE International Conference on information Systems and computer Aided Education, ICISCAE 2019

作者： Song, Yuqin Liu, Jun Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing Real-time Industrial System Wuhan China

ISBN: (纸本)9781728130668

In the study of ultrasonic elastography, displacement estimation is the most critical step. Aiming at the inefficiency of ultrasonic elastography in estimating tissue displacement and the two kinds of waveforms of ultrasonic propagation in media, a speckle tracking motion estimation based on shear wave imaging is proposed. The motion estimation of shear waves is studied by calculating the displacement using the time-domain cross-correlation. The simulation results show that the proposed algorithm is efficient and feasible. © 2019 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Hybrid optimization algorithm of particle swarm optimization with lagrangian relaxation for solving the multidimensional knapsack problem 2nd

Hybrid optimization algorithm of particle swarm optimization...

引用

2nd International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2018

作者： Luo, Jinyan Lin, Geng Zhang, Fuquan Xu, Lin Department of Mathematics Minjiang University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Digital Performance and Simulation Technology Laboratory School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Key Laboratory of Nondestructive Testing Fuqing Branch of Fujian Normal University Fuzhou350300 China

ISBN: (纸本)9783030045845

A hybrid algorithm that integrates PSO with Lagrangian relaxation is proposed for solving the multidimensional knapsack problem (MKP). An efficiency measure for MKP based on the LR dual information is defined to combine the object function and the constraints of the MKP together. The efficiency measure is used to determine the core problem for MKP with the aim of reducing the problem scale. Then a hybrid algorithm combines the Quantum Particle Swarm Optimization with a local search method is presented to solve the core problem. Numerical experiments are made on certain knapsack problems and computational results show that the proposed algorithm is very promising. © Springer Nature Switzerland AG 2019.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Small-scale Sensor Network Based on Raspberry Pi 4th

Design and Implementation of Small-scale Sensor Network Base...

引用

4th International Conference on Smart Computing and Communications, SmartCom 2019

作者： Zheng, Honglei Guo, Hong Wu, Shimin College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9783030341381

With the development of modern technology, embedded technology has continued to develop. In the deep cooperation between embedded and wireless network technologies, the technology of sensor network has been born. The software system based on traditional wireless network cannot collect data in the real world. In some production environments, the embedded sensor network consists of a large number of sensor nodes, integrating sensing, acquisition, processing, and transceiving functions into an autonomous network system to achieve dynamic and intelligent collaborative sensing of the physical world. Based on the existing wireless sensor network system architecture, this paper designs and implements a small-scale sensor network system based on Raspberry Pi. After the software and hardware test of the sensor network system, the test results show that the system can complete the information collection and transmission, and has stability and synchronization to meet project requirements and stability requirements. © 2019, Springer Nature Switzerland AG.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework

arXiv

引用

arXiv 2025年

作者： Wu, Wentao Wang, Xiao Li, Chenglong Jiang, Bo Tang, Jin Luo, Bin Liu, Qi Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China School of Artificial Intelligence Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China University of Science and Technology of China Hefei230601 China

Event cameras have attracted increasing attention in recent years due to their advantages in high dynamic range, high temporal resolution, low power consumption, and low latency. Some researchers have begun exploring pre-training directly on event data. Nevertheless, these efforts often fail to establish strong connections with RGB frames, limiting their applicability in multi-modal fusion scenarios. To address these issues, we propose a novel CM3AE pretraining framework for the RGB-Event perception. This framework accepts multi-modalities/views of data as input, including RGB images, event images, and event voxels, providing robust support for both event-based and RGB-event fusion based downstream tasks. Specifically, we design a multi-modal fusion reconstruction module that reconstructs the original image from fused multi-modal features, explicitly enhancing the model’s ability to aggregate cross-modal complementary information. Additionally, we employ a multi-modal contrastive learning strategy to align cross-modal feature representations in a shared latent space, which effectively enhances the model’s capability for multimodal understanding and capturing global dependencies. We construct a large-scale dataset containing 2,535,759 RGB-Event data pairs for the pre-training. Extensive experiments on five downstream tasks fully demonstrated the effectiveness of CM3AE. Source code and pre-trained models will be released on https://***/EventAHU/CM3AE. Copyright © 2025, The Authors. All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Research on Construction and Feature Analysis of Similarity-based Tibetan Word Co-occurrence Networks 19

A Research on Construction and Feature Analysis of Similarit...

引用

19th Chinese National Conference on Computational Linguistic, CCL 2020

作者： Jia, Yang-Dongzhou Cai, Zhi-Jie Cai, Rang-Zhuoma San, Mao-Cuo College of Computer Science and Technology Qinghai Normal University Qinghai Xining810016 China School of Computer Science and Technology Southwest Minzu University Sichuan Chengdu610041 China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Qinghai Xining810008 China Key Laboratory of Tibetan Information Processing Ministry of Education Qinghai Xining810008 China

As the crystallization of human wisdom and civilization, Language is a complex system formed after a long evolution. Language concurrency network utilizes complex network techniques to study the linguistic features and reveal the internal structure of languages. In this work, we analyze the modular structure co-occurrence network and proposes a similarity-based method for constructing Tibetan word co-occurrence networks, in which Tibetan words serve as the nodes, and the similarity metrics among words serve as the edges. We established of similarity-based word co-occurrence network on three types of documents in terms of size, namely, large, medium and small, and analyzed their statistical features. The experimental data indicated that the Tibetan word co-occurrence networks have small-world effects and scale-free features. © 2020 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Learning Representation for Clustering via Prototype Scattering and Positive Sampling

arXiv

引用

arXiv 2021年

作者： Huang, Zhizhong Chen, Jie Zhang, Junping Shan, Hongming The Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai201210 China

Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative pairs learn uniform representations for clustering, in which negative pairs, however, may inevitably lead to the class collision issue and consequently compromise the clustering performance. Non-contrastive-based methods, on the other hand, avoid class collision issue, but the resulting non-uniform representations may cause the collapse of clustering. To enjoy the strengths of both worlds, this paper presents a novel end-to-end deep clustering method with prototype scattering and positive sampling, termed ProPos. Specifically, we first maximize the distance between prototypical representations, named prototype scattering loss, which improves the uniformity of representations. Second, we align one augmented view of instance with the sampled neighbors of another view—assumed to be truly positive pair in the embedding space—to improve the within-cluster compactness, termed positive sampling alignment. The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness. By optimizing ProPos in an end-to-end expectation-maximization framework, extensive experimental results demonstrate that ProPos achieves competing performance on moderate-scale clustering benchmark datasets and establishes new state-of-the-art performance on large-scale datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Cluster analysis

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：