检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China

This paper addresses two vital challenges in Unsupervised Domain Adaptation (UDA) with a focus on harnessing the power of Vision-Language Pre-training (VLP) models. Firstly, UDA has primarily relied on ImageNet pre-trained models. However, the potential of VLP models in UDA remains largely unexplored. The rich representation of VLP models holds significant promise for enhancing UDA tasks. To address this, we propose a novel method called Cross-Modal Knowledge Distillation (CMKD), leveraging VLP models as teacher models to guide the learning process in the target domain, resulting in state-of-the-art performance. Secondly, current UDA paradigms involve training separate models for each task, leading to significant storage overhead and impractical model deployment as the number of transfer tasks grows. To overcome this challenge, we introduce Residual Sparse Training (RST) exploiting the benefits conferred by VLP's extensive pre-training, a technique that requires minimal adjustment (approximately 0.1%∼0.5%) of VLP model parameters to achieve performance comparable to fine-tuning. Combining CMKD and RST, we present a comprehensive solution that effectively leverages VLP models for UDA tasks while reducing storage overhead for model deployment. Furthermore, CMKD can serve as a baseline in conjunction with other methods like FixMatch, enhancing the performance of UDA. Our proposed method outperforms existing techniques on standard benchmarks. Our code will be available at: https://***/Wenlve-Zhou/VLP-UDA. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Gradient Coupled Flow: Performance Boosting on Network Pruning by Utilizing Implicit Loss Decrease

SSRN

引用

SSRN 2022年

作者： Kang, Xiatao Li, Ping Wu, Jiaying Yao, Jiayi School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp Changsha410114 China

Network pruning prior to training makes generalization more challenging than ever, while recent studies mainly focus on the trainability of the pruned networks in isolation. This paper explores a new perspective on loss implicit decrease of the data to be trained caused by one-batch training during each round, whose first-order approximation we term gradient coupled flow. We thus present a criterion sensitive to gradient coupled flow (GCS), which is hypothesized to capture those weights most sensitive to performance boosting at initialization. Evaluations are empirically investigated on multiple datasets such as CIFAR10/100, Tiny-ImageNet and MNIST deployed on VGG and ResNet architectures. It is shown that GCS achieves decent performance in both single pruning and iterative pruning before training. In addition, a variant of GCS called GCS-Group performs better at low compression ratios, further confirming the role of implicit loss. Interestingly, our explorations show there exists a linear correlation between generalization and implicit loss decrease based measurements on previous works as well as GCS, which ideally describes causes of accuracy fluctuation in a fine-grained manner. © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Parallelizable Counterfactual Generation Method Based on Gradient Optimization 29

A Parallelizable Counterfactual Generation Method Based on G...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Ding, Haorun Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China State Key Laboratory of High-end Server and Storage Technology Jinan China

ISBN: (纸本)9798350330717

Post-hoc explanations are important for people to understand the predictions of explanation models. One class of methods in post-hoc explanation is the generation of counterfactuals, where a hypothetical example is obtained by perturbing the inputs to show how one could obtain a different prediction from the decision model. Counter-factual explanations should satisfy several properties: One is that counterfactuals generated under specific scenarios and constraints should be feasible for users, i.e., they should accommodate different causal constraints. The other is that it is more desirable for users to have a wider variety of viable examples, i.e., counterfactual diversity. To this end, we propose a parallelizable method based on gradient optimization. We partition the input feasible domains, perform counterfactual generation independently for each feasible domain, and then parallelize the counterfactual generation process for each feasible domain. Experimental results show that our approach effectively improves the diversity, sparsity, and proximity of the generated counterfactual instances on the public datasets Adult-Income, Lending-Club, German-Credit, and COMPAS compared to other models. © 2023 IEEE.

关键词： counterfactual explanation machine learning parallel computing

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Vertical Scaling for Hybrid Deployment in Cloud Computing 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Cao, Jianqi Li, Guiying Yang, Peng Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

To maximize the CPU utilization of the server, offline tasks are usually deployed to the same server where the online service is running. Considering the necessity to ensure the service quality of online services, it is common practice to isolate the resources of online services. How to set the resource quota for online services not only affects the service quality of online services, but also affects the number and the stability of offline tasks that can be run on the server. Traditional rule-based methods or prediction-based methods will cause over-provision and fail to consider the stability of offline tasks, which often cannot achieve stability and efficiency. In this paper, reinforcement learning is proposed for the first time to solve the hybrid deployment of online services and offline tasks and dynamically adjust the resource quota of online services more effectively. Compared with the original state of the server, our proposed method reduces CPU idleness rate by 35.32% and increases CPU resource utilization rate by 3.84%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Large Language Models as Evolutionary Optimizers 13

Large Language Models as Evolutionary Optimizers

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Liu, Shengcai Chen, Caishun Qu, Xinghua Tang, Ke Ong, Yew-Soon Southern University of Science and Technology Centre for Frontier Ai Research A∗star Department of Computer Science and Engineering China Centre for Frontier Ai Research A∗star Singapore Tianqiao & Chrissy Chen Institute China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering China Nanyang Technological University Centre for Frontier Ai Research A∗star College of Computing and Data Science Singapore

ISBN: (纸本)9798350308365

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory performance. In this work, we present the first study on large language models (LLMs) as evolutionary combinatorial optimizers. The main advantage is that it requires minimal domain knowledge and human efforts, as well as no additional training of the model. This approach is referred to as LLM-driven EA (LMEA). Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions. Then, LMEA evaluates these new solutions and include them into the population for the next generation. LMEA is equipped with a self-adaptation mechanism that controls the temperature of the LLM. This enables it to balance between exploration and exploitation and prevents the search from getting stuck in local optima. We investigate the power of LMEA on the classical traveling salesman problems (TSPs) widely used in combinatorial optimization research. Notably, the results show that LMEA performs competitively to traditional heuristics in finding high-quality solutions on TSP instances with up to 20 nodes. Additionally, we also study the effectiveness of LLM-driven crossover/mutation and the self- adaptation mechanism in evolutionary search. In summary, our results reveal the great potentials of LLMs as evolutionary optimizers for solving combinatorial problems. We hope our research shall inspire future explorations on LLM-driven EAs for complex optimization challenges. © 2024 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Azimuth Ambiguity Suppression for Sparse SAR Imaging Based on Unfolded Deep Network 15

Azimuth Ambiguity Suppression for Sparse SAR Imaging Based o...

引用

15th European Conference on Synthetic Aperture Radar, EUSAR 2024

作者： Wu, Yuwei Zhang, Zhe Song, Ruizhen Qiu, Xiaolan Yu, Weidong Department of Space Microwave Remote Sensing System Beijing100090 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9783800762873

Sparse synthetic aperture radar (SAR) imaging allows for a reduction in the azimuth sampling rate based on compressive sensing theory. However, it relies on the sparsity of scenes, which can lead to significant azimuth ambiguity. To address this issue, we introduce a novel network designed to suppress azimuth ambiguity for sparse SAR imaging. Our proposed deep unfolded network is based on the Iterative Thresholding Algorithm Learned (LISTA). We replace the observation matrix with Matched Filter (MF) operators to reduce computational complexity. Experiments with real SAR scene data demonstrate the effectiveness and superiority of our approach in suppressing azimuth ambiguity. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

End-to-End Remote Sensing Image Scene Classification with Vision Transformers 23

End-to-End Remote Sensing Image Scene Classification with Vi...

引用

6th International Conference on big data Technologies, ICBDT 2023

作者： Yuan, Hao Liu, Kun Shi, Jiechuan Wang, Can Wang, Weiwei School of Information Science and Engineering University of Jinan Jinan250022 China China High-resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China QiLu Research Institute Jinan250200 China

ISBN: (纸本)9798400707667

In recent years, the development of deep learning technology has led to widespread attention on Vision Transformer (ViT) as an emerging image classification method. Remote sensing image classification is an important task in the field of remote sensing, with extensive application prospects. This paper aims to explore the remote sensing image classification method based on Vision Transformer, addressing the limitations of traditional convolutional neural networks in terms of global perception capability, context information retrieval, and positional encoding. The classification performance of the Vision Transformer model is evaluated and compared on remote sensing datasets. Vision Transformer is a deep neural network model based on self-attention mechanism that can capture the global context information in images and has achieved remarkable performance in various computer vision tasks. Furthermore, experimental results demonstrate that the remote sensing image classification method based on Vision Transformer exhibits outstanding accuracy and generalization ability. Compared to traditional convolutional neural networks, it can better capture the global features in remote sensing images and has better scalability when dealing with large-scale remote sensing image data. Experimental results on different remote sensing image datasets show that the model performs well compared to state-of-the-art methods. Specifically, Vision Transformer achieves average classification accuracies of 95.41%, 98.26%, 93.74% and 95.25% on the AID, UC-Merced, NWPU-RESISC45 and Optimal31 datasets, respectively. © 2023 ACM.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Study on Aerodynamic Breakup of Non-Newtonian Liquid Droplets and the Distribution Characteristics of Their Sub Droplets

SSRN

引用

SSRN 2024年

作者： Qian, Lijuan Cheng, Lijun Sun, Chengbin Lv, Li College of Mechanical and Electrical Engineering China Jiliang University Hangzhou310018 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China jiliang University Hangzhou310018 China

In industrial applications, the secondary breakup of droplets and the size distribution of their sub droplets are crucial for the atomization performance indicators. In this work, a high-speed digital camera is utilized to experimentally and theoretically study the secondary breakup process of xanthan gum (XG) droplets and the size distribution changes of resulting sub droplets in continuous airflow by changing the Weber number and effective Ohnesorge number. In addition, a detailed study is conducted on the liquid ring with the highest liquid content. The results show that at low Weber numbers, the number of nodes generated at the XG droplet ring is the same as that of the water droplet, following "the combined R-T/aerodynamic drag" mechanism. However, the final diameter of the nodes differs significantly from that of the water droplet. The particle size of XG liquid ring nodes is not only affected by Weber number, but also decreases with the increase of effective Ohnesorge number. The particle size of the remaining broken sub droplets in the liquid ring decreases with the increase of effective Ohnesorge number. Finally, the spatial range of droplet breakup under different parameters is described by using the liquid ring breakup angle, and it is found that the breakup angle of the liquid ring is mainly related to the breakup mode. © 2024, The Authors. All rights reserved.

关键词： Non Newtonian flow

来源：评论

学校读者我要写书评

暂无评论

DMSACNN: Deep Multiscale Attentional Convolutional Neural Network for EEG-Based Motor Decoding

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Liu, Ke Xing, Xin Yang, Tao Yu, Zhuliang Xiao, Bin Wang, Guoyin Wu, Wei Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing China Chongqing University of Posts and Telecommunications Key Laboratory of Cyberspace Big Data Intelligent Security of Ministry of Education China South China University of Technology College of Automation Science and Engineering Guangzhou510641 China Chongqing Normal University National Center for Applied Mathematics in Chongqing Chongqing401331 China Shanghai Jiao Tong University School of Medicine Songjiang Hospital Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders Shanghai201600 China

Objective: Accurate decoding of electroencephalogram (EEG) signals has become more significant for the brain-computer interface (BCI). Specifically, motor imagery and motor execution (MI/ME) tasks enable the control of external devices by decoding EEG signals during imagined or real movements. However, accurately decoding MI/ME signals remains a challenge due to the limited utilization of temporal information and ineffective feature selection methods. Methods: This paper introduces DMSACNN, an end-to-end deep multiscale attention convolutional neural network for MI/ME-EEG decoding. DMSACNN incorporates a deep multiscale temporal feature extraction module to capture temporal features at various levels. These features are then processed by a spatial convolutional module to extract spatial features. Finally, a local and global feature fusion attention module is utilized to combine local and global information and extract the most discriminative spatiotemporal features. Main results: DMSACNN achieves impressive accuracies of 78.20%, 96.34% and 70.90% for hold-out analysis on the BCI-IV-2a, High Gamma and OpenBMI datasets, respectively, outperforming most of the state-of-the-art methods. Conclusion and significance: These results highlight the potential of DMSACNN in robust BCI applications. Our proposed method provides a valuable solution to improve the accuracy of the MI/ME-EEG decoding, which can pave the way for more efficient and reliable BCI systems. The source code for DMSACNN is available at https://***/xingxin-99/***. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Adrc & Mpc for Gas Pressure Energy Recovery Systems

SSRN

引用

SSRN 2024年

作者： Zhao, RuoChen Wei, Dong Xiong, YaXuan Zuo, MingXin School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China The University of Sheffield United Kingdom School of Environmental and Energy Engineering Beijing University of Civil Engineering and Architecture China Beijing Key Laboratory of Intelligent Processing for Building Big Data China

The gas pressure needs to be regulated from high to low in transmitting certain industrial gases or natural gas according to the user's demand. To reduce the effects of disturbances caused by load fluctuations on the gas user side, this paper establishes a gas pressure energy recovery control system to generate electricity using an expander-driven generator. An Active Disturbance Rejection Controller (ADRC) is designed for the generator rotational speed process, and a model predictive controller (MPC) is developed for the torque/flux linkage process;they operate in a cascaded manner. The MPC in the secondary loop is used to overcome the system time delay characteristics, thus avoiding the generator torque and flux linkage deviation from their set-points caused by gas load variations. ADRC in the primary loop observes the system disturbances and compensates for them to determine the set-point of the torque, thus ensuring a stable generator rotational speed. The proposed control strategy is verified on a gas pressure energy recovery experimental platform. A comparison of experimental results with the five currently common generator control methods shows that the proposed strategy reduces the generator speed fluctuations and the harmonic components in the generator current. © 2024, The Authors. All rights reserved.

关键词： Model predictive control

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：