检索结果-内蒙古大学图书馆

Trust Online Over-the-air Computation for Wireless Federated Learning

IEEE Transactions on Mobile computing 2025年

作者： Sun, Mingjie Zheng, Jie Du, Hongyang Zhang, Haijun Niyato, Dusit Kang, Jiawen Wang, Jiacheng Ren, Jie Gao, Ling Wang, Zheng Northwest University State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Shaanxi Xian710127 China University of Hong Kong department of electrical and electronic engineering Hong Kong University of Science and Technology Beijing Institute of Artificial Intelligence Beijing100083 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Guangdong University of Technology Automation of School Guangzhou510006 China Shaanxi Normal University School of Computer Science Xi'an710062 China University of Leeds School of Computing LS2 9JT United Kingdom

Using the wireless waveform superposition property, over-the-air computation (OAC) enables federated learning (FL) to achieve fast model aggregation. However, this computing paradigm is vulnerable to poisoning attacks due to the openness of a wireless channel over time, where malicious mobile devices can introduce cumulative errors for the global FL model in a time-varying wireless environment for each communication round. This article presents a trust online OAC (TO-OAC) scheme to minimize impacts on the global model introduced by malicious devices adjusting to dynamic attack and wireless channel fluctuations over time. TO-OAC achieves this by utilizing trustworthy security quantification of OAC for each FL training round. To optimize the cumulative training loss at the aggregation node with the long-term power and trust constraints of mobile devices, we propose a joint trust, power, and channel-aware algorithm to flexibly update local and global models in response to the dynamic changes in the wireless and secure environment. We analyze the performance limits for the aggregation of trust models, considering metrics for computation and communication through time. We then propose another trust online regularization over-the-air computation (TOR-OAC) as an improved version of the TO-OAC scheme to decrease convergence time while ensuring long-term trust and power limitation. Experimental results performed on real-life datasets show that the two proposed schemes (TO-OAC and TOR-OAC) outperform prior works, especially in noisy, time-varying wireless channels and malicious attacks. 2002-2012 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Relation-Based Cross Attention Network for Image-Text Retrieval

Semantic Relation-Based Cross Attention Network for Image-Te...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Image-text retrieval refers to querying the text or image of another modality given an image or text, and its key lies in the ability to accurately measure the similarity between text and image. Most of the existing retrieval methods only utilize the intramodal relations of each modality or the intermodal relations of the two modalities to perform the retrieval task. To address the above problems, we integrate the intra-modal and inter-modal relations and propose a Semantic Relation-based Cross Attention Network(SRCAN). In our proposed method, we first mine the possible intra-modal associations between regions in an image and between words in a text to obtain features with semantic relationships, and then capture the fine-grained associations between segments through the cross-attention mechanism. Finally, we balance the intra-modal and inter-modal relationships to improve the performance of the model. Our proposed method is experimentally validated on two datasets, Flickr30K and MS-COCO, and the experimental results show that our method achieves superior results.

关键词： Image segmentation Semantics Bidirectional control Feature extraction Cognition Feeds Cybernetics

来源：评论

学校读者我要写书评

暂无评论

MOSMOS: Multi-organ segmentation facilitated by medical report supervision

arXiv

引用

arXiv 2024年

作者： Tian, Weiwei Huang, Xinyu Hou, Junlin Ren, Caiyue Jiang, Longquan Zhao, Rui-Wei Jin, Gang Zhang, Yuejie Geng, Daoying Academy for Engineering and Technology Fudan University Shanghai200433 China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Shanghai200433 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Owing to a large amount of multi-modal data in modern medical systems, such as medical images and reports, Medical Vision-Language Pre-training (Med-VLP) has demonstrated incredible achievements in coarse-grained downstream tasks (i.e., medical classification, retrieval, and visual question answering). However, the problem of transferring knowledge learned from Med-VLP to fine-grained multi-organ segmentation tasks has barely been investigated. Multi-organ segmentation is challenging mainly due to the lack of large-scale fully annotated datasets and the wide variation in the shape and size of the same organ between individuals with different diseases. In this paper, we propose a novel pre-training & fine-tuning framework for Multi-Organ Segmentation by harnessing Medical repOrt Supervision (MOSMOS). Specifically, we first introduce global contrastive learning to maximally align the medical image-report pairs in the pre-training stage. To remedy the granularity discrepancy, we further leverage multi-label recognition to implicitly learn the semantic correspondence between image pixels and organ tags. More importantly, our pre-trained models can be transferred to any segmentation model by introducing the pixel-tag attention maps. Different network settings, i.e., 2D U-Net and 3D UNETR, are utilized to validate the generalization. We have extensively evaluated our approach using different diseases and modalities on BTCV, AMOS, MMWHS, and BRATS datasets. Experimental results in various settings demonstrate the effectiveness of our framework. This framework can serve as the foundation to facilitate future research on automatic annotation tasks under the supervision of medical reports. Copyright © 2024, 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

Semantic Information Reasoning and Multi-Step Cross-Modal Interaction Network for Image-Text Retrieval

Semantic Information Reasoning and Multi-Step Cross-Modal In...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xishan Ma Yushui Geng Jing Zhao Huanxiao Zhou 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Image-text retrieval is a basic cross-modal task, and the basic idea is to learn image-text matching. The key to this task is to accurately measure the similarity between these two modalities. However, most existing methods tend to measure image-text similarity based on highly correlated region-word pairs, which lacks the ability to capture complex cross-modal semantic associations, thereby resulting in failure to distinguish hard negative examples that are similar in semantic content. Furthermore, existing methods focus more on alignment of different modal features, thus neglecting deep reasoning about the semantic concepts within the modality. In this paper, we propose a new semantic information reasoning and multi-step cross-modal interaction (SRMCI) network to simultaneously explore intra-modal and inter-modal relationships. Specifically, we first propose a semantic information reasoning module to fully explore potential semantic relationships within modalities and focus on fragments with important semantic information. Then, we design a multi-step cross-modal interaction module that utilizes two different inter-modal interactive attentions and an effective gated fusion strategy to capture fragment-level and fragment-instance-level cross-modal semantic associations. In particular, this gated fusion strategy is used to learn better fine-grained feature representations to aid in understanding and establishing semantic associations between different modalities. Experiments on the benchmark datasets MS-COCO and Flickr30K demonstrate the effectiveness of our method.

关键词： Correlation Semantics Neural networks Logic gates Benchmark testing Cognition

来源：评论

学校读者我要写书评

暂无评论

Cross-modal retrieval based on Attention Embedded Variational Auto-Encoder

Cross-modal retrieval based on Attention Embedded Variationa...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Kaili Zhou Yiyun Xing Yushui Geng Jing Zhao Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong 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 Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This study proposes a cross-modal retrieval technique, which employs an Attention Embedded Variational AutoEncoder (AE-VAE) to tackle the problem of reduced retrieval accuracy resulting from data noise and data absence in cross-modal retrieval tasks. First, the variational auto-encoder(VAE) is used as an infrastructure to transform modal data into latent variables by encoding and decoding different modal features, thus preserving the semantic structure of the raw modal data and suppressing noise and missing information in the data. Secondly, to better capture the important semantic features of image and text modalities, an improved multi-attention module is introduced in the encoder. In addition, a cross-modal alignment module is designed to further align the latent variables of different modalities in the latent space to solve the confusion problem and improve the accuracy and robustness of cross-modal retrieval. Finally, experiments are conducted on four public datasets, CUB, SUN, AwA1 and AwA2, and the experimental results show that our proposed model is effective in improving the accuracy and robustness of retrieval.

关键词： Accuracy Uncertainty Noise Semantics Transforms Probabilistic logic Robustness

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention Network for Image-Text Matching

Semantic-Enhanced Attention Network for Image-Text Matching

引用

International Conference on computer Supported Cooperative Work in Design

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention Network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wei Ding Luyao Wang Wei Zhang Myung Jin Lee Ling Wang Kwang Woo Nam Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) 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 Industry-University Cooperstion Foundation Chungbuk National University Cheongju Korea School of Computer Science Northeast Electric Power University Jilin China School of Computer Science and Engineering Kunsan National University Gunsan Korea

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In this paper, we propose a new UAV video similarity measurement algorithm to cluster and analyze UAV videos by measuring the similarity between UAV videos and train them in sub-groups, which in turn improves the efficiency of UAV video data mining. Our preliminary work introduces the maximum common view subsequence (LCVS) to compute the similarity between UAV videos, but LCVS needs to frequently compute the common visible region of video frames generating extremely high time cost. In order to solve the problem of high computational cost of LCVS, we propose a similarity algorithm based on minimum tilted outer rectangle clustering (MTORC) for UAV videos. The MTORC algorithm adopts minimum tilted outer rectangle to cluster the field of view of the marked points in each frame, which reduces the time complexity of calculating the common visible region. By comparing experiments with LCSS and LCVS, the experimental results prove that MTORC is better than the present previous research in terms of algorithm accuracy and time cost.

关键词： Training Visualization Costs Accuracy Clustering algorithms Autonomous aerial vehicles Time measurement

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding

arXiv

引用

arXiv 2023年

作者： Pan, Wenbo Chen, Qiguang Xu, Xiao Che, Wanxiang Qin, Libo School of Computer Science and Engineering Central South University China Research Center for Social Computing and Information Retrieval China Harbin Institute of Technology China

Zero-shot dialogue understanding aims to enable dialogue to track the user’s needs without any training data, which has gained increasing attention. In this work, we investigate the understanding ability of ChatGPT for zero-shot dialogue understanding tasks including spoken language understanding (SLU) and dialogue state tracking (DST). Experimental results on four popular benchmarks reveal the great potential of ChatGPT for zero-shot dialogue understanding. In addition, extensive analysis shows that ChatGPT benefits from the multi-turn interactive prompt in the DST task but struggles to perform slot filling for SLU. Finally, we summarize several unexpected behaviors of ChatGPT in dialogue understanding tasks, hoping to provide some insights for future research on building zero-shot dialogue understanding systems with Large Language Models (LLMs). Copyright © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation-Oriented Joint Array Partitioning and Beamforming Designs for ISAC Systems

arXiv

引用

arXiv 2024年

作者： Liu, Rang Li, Ming Liu, Qian Swindlehurst, A. Lee Center for Pervasive Communications and Computing University of California IrvineCA92697 United States School of Information and Communication Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

Integrated sensing and communication has been identified as an enabling technology for forthcoming wireless networks. In an effort to achieve an improved performance trade-off between multiuser communications and radar sensing, this paper considers a dynamically-partitioned antenna array architecture for monostatic ISAC systems, in which each element of the array at the base station can function as either a transmit or receive antenna. To fully exploit the available spatial degrees of freedom for both communication and sensing functions, we jointly design the partitioning of the array between transmit and receive antennas together with the transmit beamforming in order to minimize the direction-of-arrival (DOA) estimation error, while satisfying constraints on the communication signal-to-interference-plus-noise ratio and the transmit power budget. An alternating algorithm based on Dinkelbach’s transform, the alternative direction method of multipliers, and majorization-minimization is developed to solve the resulting complicated optimization problem. To reduce the computational complexity, we also present a heuristic three-step strategy that optimizes the transmit beamforming after determining the antenna partitioning. Simulation results confirm the effectiveness of the proposed algorithms in significantly reducing the DOA estimation error. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Sensor Localization by Few Distance Measurements via the Intersection of Implicit Manifolds

Sensor Localization by Few Distance Measurements via the Int...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Michael M. Bilevich Steven M. LaValle Dan Halperin Blavatnik School of Computer Science Tel-Aviv University Israel Center for Ubiquitous Computing Faculty of Information Technology and Electrical Engineering University of Oulu Finland

We present a general approach for determining the unknown (or uncertain) position and orientation of a sensor mounted on a robot in a known environment, using only a few distance measurements (between 2 to 6 typically), which is advantageous, among others, in sensor cost, and storage and information-communication resources. In-between the measurements, the robot can perform predetermined local motions in its workspace, which are useful for narrowing down the candidate poses of the sensor. We demonstrate our approach for planar workspaces, and show that, under mild transversality assumptions, already two measurements are sufficient to reduce the set of possible poses to a set of curves (one-dimensional objects) in the three-dimensional configuration space of the sensor $\mathbb{R}^{2}\times \mathbb{S}^{1},$ and three or more measurements reduce the set of possible poses to a finite collection of points. However, analytically computing these potential poses for non-trivial intermediate motions between measurements raises substantial hardships and thus we resort to numerical approximation. We reduce the localization problem to a carefully tailored procedure of intersecting two or more implicitly defined two-manifolds, which we carry out to any desired accuracy, proving guarantees on the quality of the approximation. We demonstrate the real-time effectiveness of our method even at high accuracy on various scenarios and different allowable intermediate motions. We also present experiments with a physical robot. Our open-source software and supplementary materials are available at https://***/taucgl/vb-fdml-public.

关键词：

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：