检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Song, Shanshan Li, Jiangyun Wang, Jing Cai, Yuanxiu Dong, Wenkai School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing China Shunde Innovation School University of Science and Technology Beijing Foshan China

There is a key problem in the medical visual question answering task that how to effectively realize the feature fusion of language and medical images with limited datasets. In order to better utilize multi-scale information of medical images, previous methods directly embed the multi-stage visual feature maps as tokens of same size respectively and fuse them with text representation. However, this will cause the confusion of visual features at different stages. To this end, we propose a simple but powerful multi-stage feature fusion method, MF2-MVQA, which stage-wise fuses multi-level visual features with textual semantics. MF2-MVQA achieves the State-Of-The-Art performance on VQA-Med 2019 and VQA-RAD dataset. The results of visualization also verify that our model outperforms previous work. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Joint Statistical and Causal Feature Modulated Face Anti-Spoofing

Joint Statistical and Causal Feature Modulated Face Anti-Spo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xin Dong Tao Wang Zhendong Li Hao Liu School of Information Engineering Ningxia University Yinchuan China Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-Founded by Ningxia Municipality and Ministry of Education Yinchuan China Key Laboratory of the Internet of Water and Digital Water Governance of the Yellow River in Ningxia Yinchuan China

In this paper, we propose a hierarchical feature modulation (HFM) approach for stable face anti-spoofing in unseen domains and unseen attacks. The conventional multi-domain based generalizable approaches likely lead to local optima due to the complicated or heuristic learning paradigm. Inspired by the fact that high-level semantic disturbances and low-level miscellaneous bias jointly cause the distribution shift, HFM aims to modulate the fine-grained feature in a hierarchical manner. Specifically, we complement the structural feature with patch-wise learnable statistical information, i.e. local difference histogram, to relieve the overfitting on high-level semantics. We further introduce the structural causal model (SCM) with imaging color model to reveal that presenting mediums and capturing devices destroy the liveness-relevant information from the low level. Thus we model this hidden entanglement as a distribution mixture problem and propose the expectation-maximization (EM) based causal intervention to remove these miscellanies. Experimental results on public datasets demonstrate the effectiveness of HFM, especially in out-of-distribution settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Fourier Feature for Medical Image Synthesis

Cross-Modality Fourier Feature for Medical Image Synthesis

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Mei Ma Ling Lin Heng Wang Zhendong Li Hao Liu School of Information Engineering Ningxia University Yinchuan China Collaborative Innovation Center for Ningxia Big Data and Artiffcial Intelligence Co-Founded by Ningxia Municipality and Ministry of Education Yinchuan China Key Laboratory of the Internet of Water and Digital Water Governance of the Yellow River in Ningxia Yinchuan China

In this paper, we propose a cross-modality fourier feature (CMFF) method via frequency selection, which learns the rational anatomical structure for targeting medical modality images. Unlike existing works seeking pixel-wise intensity discrepancy likely misleading to bias anatomical structures, our approach strongly holds the medical prior that different modality MRI images should share the same anatomical structure. To achieve this, our method instead learns to convert MRI images to the auxiliary frequency domain. Moreover, we adopt the Shapley value to quantify the contribution of each frequency, with respect to the structure for MRI image pairs of different modalities. Thus our approach learns to refine the anatomical structure generated by the target modality iteratively. Extensive experimental results on the BraTS dataset show that our model surpasses the performance compared to SOTAs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Correction Adaptation Network for Noisy knowledge Transfer

arXiv

引用

arXiv 2022年

作者： Wang, Yunyun Zheng, Weiwen Chen, Songcan The Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Computer Science and Engineering Nanjing University of Posts & Telecommunications Nanjing210046 China The MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Computer Science & Technology/AI Nanjing University of Aeronautics & Astronautics Nanjing210023 China

Previous unsupervised domain adaptation (UDA) methods aim to promote target learning via a single-directional knowledge transfer from label-rich source domain to unlabeled target domain, while its reverse adaption from target to source has not jointly been considered yet so far. In fact, in some real teaching practice, a teacher helps students learn while also gets promotion from students to some extent, which inspires us to explore a dual-directional knowledge transfer between domains, and thus propose a Dual-Correction Adaptation Network (DualCAN) in this paper. However, due to the asymmetrical label knowledge across domains, transfer from unlabeled target to labeled source poses a more difficult challenge than the common source-to-target counterpart. First, the target pseudo-labels predicted by source commonly involve noises due to model bias, hence in the reverse adaptation, they may hurt the source performance and bring a negative target-to-source transfer. Secondly, source domain usually contains innate noises, which will inevitably aggravate the target noises, leading to noise amplification across domains. To this end, we further introduce a Noise Identification and Correction (NIC) module to correct and recycle noises in both domains. To our best knowledge, this is the first naive attempt of dual-directional adaptation for noisy UDA, and naturally applicable to noise-free UDA. A theory justification is given to state the rationality of our intuition. Empirical results confirm the effectiveness of DualCAN with remarkable performance gains over state-of-the-arts, particularly for extreme noisy tasks (e.g., ∼+ 15% on Pw→Pr and Pr→Rw of Office-Home). Copyright © 2022, The Authors. All rights reserved.

关键词： knowledge management

来源：评论

学校读者我要写书评

暂无评论

Wireless Powered IoE for 6G: Massive Access Meets Scalable Cell-Free Massive MIMO

引用

China Communications 2020年第12期17卷 92-109页

作者： Shuaifei Chen Jiayi Zhang Yu Jin Bo Ai School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong UniversityBeijing 100044China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou UniversityZhengzhou 450001China

A key challenge to the scalable deployment of the energy self-sustainability(ESS)Internet of Everything(IoE)for sixth-generation(6G)networks is juggling massive connectivity and high spectral efficiency(SE).Cell-free massive multiple-input multiple-output(CF mMIMO)is considered as a promising solution,where many wireless access points perform coherent signal processing to jointly serve the ***,massive connectivity and high SE are difficult to obtain at the same time because of the limited pilot *** solve this problem,we propose a new framework for ESS IoE networks where the user activity detection(UAD)and channel estimation are decoupled.A UAD detector based on deep convolutional neural networks,an initial access scheme,and a scalable power control policy are proposed to enable the practical scalable CF mMIMO *** derive novel and exact closed-form expressions of harvested energy and SE with maximum ratio(MR)*** local partial minimum mean-square error and MR combining,simulation results prove that the proposed framework can serve more users,improve the SE performance,and achieve better user fairness for the considered ESS IoE networks.

关键词： 6G network cell-free massive MIMO energy self-sustainability Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

A Ji-shaped Chinese-character millimeter-wave antenna for 5G communications 4

A Ji-shaped Chinese-character millimeter-wave antenna for 5G...

引用

4th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2021

作者： Yang, Baifa Huang, Haixuan Feng, Botao Deng, Li College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9781665432030

A Ji-shaped Chinese-character patch antenna is proposed for future communications. The proposed antenna is comprised of two dielectric layers. Ji-shaped patch is etched on the upper surface of the top layer, whereas a feeding network is designed in the other layer. Furthermore, the conformal Jishaped antenna is designed to be placed on the surface of the cylindrical objects. Simulated results demonstrate that a gain of 7.9±0.3 dBi over the whole operating frequency band (24.75-27.5 GHz) can be obtained. © 2021 IEEE

关键词： Substrate integrated waveguides

来源：评论

学校读者我要写书评

暂无评论

Distributed Active Disturbance Rejection Control of Multiple Mobile Robots for Online Workload Partition

Distributed Active Disturbance Rejection Control of Multiple...

引用

Chinese Automation Congress (CAC)

作者： Xin Li Chao Zhai Hehong Zhang Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Wuhan Campus School of Automation Wuhan China School of Computer and Data Science Fuzhou University Fuzhou China

Considering the actual multi-agent coverage process, the motion trajectories are seriously affected by disturbances and noise. In this paper, a cooperative control method based on active disturbance rejection controller (ADRC) for multiple mecanum-wheeled robots (MWMR) is proposed to improve its robustness. In particular, to suppress the total disturbances during the running of each robot and reduce large computation and observation cost of high order ADRC, a reduced-order cascaded ADRC (RC-ADRC) is proposed. Moreover, distributed controller is proposed to track the expected trajectories of multiple mecanum-wheeled robots under disturbances. Compared with the proposed RC-ADRC based cooperative control scheme and PID based cooperative control one, the favorable motion trajectory tracking performance is obtained. Simulation results verify the superiority of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enclosing Control of Hybrid Multi-Agent Systems

SSRN

引用

SSRN 2023年

作者： Jia, Yapeng Zhao, Qi Zhang, Dong Zheng, Yuanshi School of Data Science Qingdao University of Science and Technology Qingdao266061 China Shaanxi Key Laboratory of Space Solar Power Station System School of Mechano-Electronic Engineering Xidian University Xi’an710071 China School of Astronautics Northwestern Polytechnical University Xi’an710072 China

This paper investigates the enclosing control of hybrid multi-agent systems under directed networks. Firstly, we establish some criteria for continuoustime and discrete-time multi-agent systems to achieve enclosing control. Secondly, according to the communication modes among agents, four distributed enclosing control protocols are proposed for hybrid multi-agent systems. Then, under the proposed protocols, we give the corresponding sufficient conditions to guarantee enclosing control. Finally, the correctness of our results is verified by simulations. © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Carsharing Equitable Relocation Problem: A Two-Stage Stochastic Programming Approach with Learning-Embedded Endogenous Uncertainty in Demand

SSRN

引用

SSRN 2022年

作者： Zhang, Si Sun, Huijun Liu, Yang Lv, Ying Wu, Jianjun Feng, Xiaoyan Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing China Department of Civil and Environmental Engineering National University of Singapore Singapore Department of Industrial Systems Engineering and Management National University of Singapore Singapore State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

Uncertain demand may lead to inefficient carsharing decisions. Under this case, the supply-demand imbalance problem for a station-based one-way carsharing system would be more challenging, thus complicating the vehicle relocation decisions. This work proposes a two-stage stochastic mixed-integer nonlinear programming model, which integrates the long-term and short-term decisions to maximize the profit of the carsharing companies. In the first stage, the tactical decisions of fleet sizing and vehicle initial distribution are optimized before the realization of the uncertain demand. In the second stage, the operational decisions of operator-based and user-based relocation are determined. First, this paper considers that the distribution of uncertain demand can be affected by the operational decisions of user-based relocation incentives. A learning-embedded optimization method is introduced to learn the distribution of demand. In this way, the decision-making optimization model can achieve higher levels of performance under the guidance of the demand uncertainty learning model. Second, an equitable relocation problem, considering the uneven demand unsatisfied levels with two different equity criteria from the aspects of station and OD pair is presented, respectively. Third, the large number of discrete decision variables, nonlinear operational cost function and constraints, and nonlinearities from the endogenous demand uncertainty together constitute the solving challenges of the proposed model. For solving the problem efficiently, a dedicated two-phase solution algorithm is proposed, with a learning-embedded trust-region method adopted to solve the continuous relaxation problem in phase I, and a mixed-integer linear programming guided iterative rounding to obtain the integer solutions of carsharing operations in phase II. The solution algorithm adaptively bridges the learning and optimization via the trust-region method with flexible sample generation. Finally

关键词： Stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Revisiting Few-Shot Learning from a Causal Perspective

arXiv

引用

arXiv 2022年

作者： Lin, Guoliang Xu, Yongheng Lai, Hanjiang Yin, Jian School of Computer Science and Engineering Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-Sen University China

Few-shot learning with N-way K-shot scheme is an open challenge in machine learning. Many metric-based approaches have been proposed to tackle this problem, e.g., the Matching Networks and CLIP-Adapter. Despite that these approaches have shown significant progress, the mechanism of why these methods succeed has not been well explored. In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism. We show that the existing approaches can be viewed as specific forms of front-door adjustment, which can alleviate the effect of spurious correlations and thus learn the causality. This causal interpretation could provide us a new perspective to better understand these existing metric-based methods. Further, based on this causal interpretation, we simply introduce two causal methods for metric-based few-shot learning, which considers not only the relationship between examples but also the diversity of representations. Experimental results demonstrate the superiority of our proposed methods in few-shot classification on various benchmark datasets. Code is available in https://***/lingl1024/causalFewShot. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

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：