检索结果-内蒙古大学图书馆

Enhancing 3D medical image registration with cross attention, residual skips, and cascade attention

intelligent Data Analysis 2025年第1期29卷 186-201页

作者： Anwar, Muhammad He, Zhiquan Cao, Wenming College of Electronics and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

At the core of Deep Learning-based Deformable Medical Image Registration (DMIR) lies a strong foundation. Essentially, this network compares features in two images to identify their mutual correspondence, which is necessary for precise image registration. In this paper, we use three novel techniques to increase the registration process and enhance the alignment accuracy between medical images. First, we propose cross attention over multi-layers of pairs of images, allowing us to take out the correspondences between them at different levels and improve registration accuracy. Second, we introduce a skip connection with residual blocks between the encoder and decoder, helping information flow and enhancing overall performance. Third, we propose the utilization of cascade attention with residual block skip connections, which enhances information flow and empowers feature representation. Experimental results on the OASIS data set and the LPBA40 data set show the effectiveness and superiority of our proposed mechanism. These novelties contribute to the enhancement of 3D DMIR-based on unsupervised learning with potential implications in clinical practice and research. © 2024 – IOS Press. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Stacked Network Method for Enhancing the Performance of Side-Channel Attacks

引用

Computers, Materials & Continua 2025年第4期83卷 1001-1022页

作者： Zhicheng Yin Lang Li Yu Ou College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application HengyangNormal UniversityHengyang421002China

The adoption of deep learning-based side-channel analysis(DL-SCA)is crucial for leak detection in secure *** previous studies have applied this method to break targets protected with *** the increasing number of studies,the problem of model *** research mainly focuses on exploring hyperparameters and network architectures,while offering limited insights into the effects of external factors on side-channel attacks,such as the number and type of *** paper proposes a Side-channel Analysis method based on a Stacking ensemble,called *** our method,multiple models are deeply *** the extended application of base models and the meta-model,Stacking-SCA effectively improves the output class probabilities of the model,leading to better ***,this method shows that the attack performance is sensitive to changes in the number of ***,five independent subsets are extracted from the original ASCAD database as multi-segment datasets,which are mutually *** method shows how these subsets are used as inputs for Stacking-SCA to enhance its attack *** experimental results show that Stacking-SCA outperforms the current state-of-the-art results on several considered datasets,significantly reducing the number of attack traces required to achieve a guessing entropy of ***,different hyperparameter sizes are adjusted to further validate the robustness of the method.

关键词： Side-channel analysis deep learning stacking ensemble learning model generalization

来源：评论

学校读者我要写书评

暂无评论

DeepHGNN: A Novel Deep Hypergraph Neural Network

引用

Chinese Journal of Electronics 2022年第5期31卷 958-968页

作者： LIN Jingjing YE Zhonglin ZHAO Haixing FANG Lusheng College of Computer Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Xining Urban Vocational & Technical College

With the development of deep learning,graph neural networks(GNNs) have yielded substantial results in various application fields. GNNs mainly consider the pair-wise connections and deal with graph-structured data. In many real-world networks, the relations between objects are complex and go beyond *** is a flexible modeling tool to describe intricate and higher-order correlations. The researchers have been concerned how to develop hypergraph-based neural network model. The existing hypergraph neural networks show better performance in node classification tasks and so on, while they are shallow network because of oversmoothing, over-fitting and gradient vanishment. To tackle these issues, we present a novel deep hypergraph neural network(Deep HGNN). We design Deep HGNN by using the technologies of sampling hyperedge, residual connection and identity mapping, residual connection and identity mapping bring from graph convolutional neural networks. We evaluate Deep HGNN on two visual object datasets. The experiments show the positive effects of Deep HGNN, and it works better in visual object classification tasks.

关键词： Deep neural networks Graph neural network Hypergraph neural network Deep hypergraph neural network

来源：评论

学校读者我要写书评

暂无评论

Neural-based prescribed-time consensus control for multiagent systems via dynamic memory event-triggered mechanism

引用

Science China(Technological Sciences) 2025年第3期68卷 217-227页

作者： Xiaohong ZHENG Hui MA Qi ZHOU Hongyi LI School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Controland Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative ControlGuangdong University of TechnologyGuangzhou510006China School of Mathematics and Statistics Guangdong University of TechnologyGuangzhou510006China College of Electronic and Information Engineering and the Chongqing Key Laboratory of Generic Technology and System of Service Robots Southwest UniversityChongqing400715China

This work investigates the implementation of distributed prescribed-time neural network(NN)control for nonlinear multiagent systems(MASs)using a dynamic memory event-triggered mechanism(DMETM).First,it introduces a composite learning technique in NN *** method leverages the prediction error within the NN update law to enhance the accuracy of the unknown nonlinearity ***,by introducing a time-varying transformation,the study establishes a distributed prescribed-time control *** notable feature of this algorithm is its ability to predetermine the convergence time independently of initial conditions or control ***,the DMETM is established to reduce the actuation frequency of the *** the conventional memoryless dynamic event-triggered mechanism,the DMETM incorporates a memory term to further increase triggering *** a distributed estimator for the leader,the DMETM-based NN prescribed-time controller is designed in a fully distributed manner,which guarantees that all signals in the closed-loop system remain bounded within the prescribed ***,simulation results are presented to validate the effectiveness of the proposed algorithm.

关键词： consensus control composite learning control dynamic memory event-triggered control prescribed-time control multiagent systems(MASs)

来源：评论

学校读者我要写书评

暂无评论

MSCTGAN: Conformer Improvements for Speech Enhancement 17

MSCTGAN: Conformer Improvements for Speech Enhancement

引用

17th IEEE International Conference on Signal processing, ICSP 2024

作者： Wu, Zhengyu Zheng, Nengheng College of Electronics and Information Engineering Shenzhen University The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)9798350387384

Convolution-augmented transformer (Conformer) has shown impressive performance in speech enhancement. However, it employs a single fixed large kernel convolutional block for local feature modeling, which limits its attention to local features. Also, modeling the entire frequency band in the same manner hinders the model from focusing on more critical sub band information, resulting in low performance. To address these two issues, we propose a GAN-based approach called Multi-Scale Convolution-augmented Transformer GAN (MSCTGAN) for speech enhancement. MSCTGAN incorporates several stacks of MSCT modules to better capture local features. Taking into account the varying importance of speech sub-bands, these features are introduced in frequency domain relative position encoding and loss function, which facilitated the fusion of both full-band and sub-band information. The objective evaluation demonstrates the competitive performance of MSCTGAN compared to models utilizing conventional Transformer and Conformer architectures. © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Dive into Coarse-to-Fine Strategy in Single Image Deblurring 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Li, Zebin Luo, Jianping Guangdong Key Laboratory of Intelligent Information Processing College of Electronic and Information Engineering Shenzhen University Shenzhen China

ISBN: (数字)9783031533051

ISBN: (纸本)9783031533044

The coarse-to-fine approach has gained significant popularity in the design of networks for single image deblurring. Traditional methods used to employ U-shaped networks with a single encoder and decoder, which may not adequately capture complex motion blur patterns. Inspired by the concept of multi-task learning, we dive into the coarse-to-fine strategy and propose an all-direction, multi-input and multi-output network for image deblurring (ADMMDeblur). ADMMDeblur has two distinct features. Firstly, it employs four decoders, each generating a unique residual representing a specific motion direction. This enables the network to effectively address motion blur in all directions within a two-dimensional (2D) scene. Secondly, the decoders utilize kernel rotation and sharing, which ensures the decoders do not separate unnecessary components. Consequently, the network exhibits enhanced efficiency and deblurring performance while requiring fewer parameters. Extensive experiments conducted on the GoPro and HIDE datasets demonstrate that our proposed network achieves better performance in deblurring accuracy and model size compared to existing well-performing methods. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Formation Tracking control of Heterogeneous Multi-Agent Systems With Intermittent Communications and Directed Switching Networks

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 294-296页

作者： Yuhan Wang Zhuping Wang Hao Zhang Huaicheng Yan the Shanghai Research Institute for Intelligent Autonomous Systems Tongji University the National Key Laboratory of Autonomous Intelligent Unmanned Systems the Frontiers Science Center for Intelligent Autonomous System of Ministry of Education the College of Electronic and Information Engineering the Department of Control Science and Engineering Tongji University the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education the School of Information Science and Engineering East China University of Science and Technology

Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so... 详细信息

关键词： Switches Topology Observers Formation control Event detection Switched systems Multi-agent systems control theory Autonomous systems Stability

来源：评论

学校读者我要写书评

暂无评论

Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection 38

Improving Viewpoint-Independent Object-Centric Representatio...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Huang, Yinxuan Gao, Chengmin Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random or sequential viewpoint selection strategies. While applicable across various scenes, these strategies may not always be ideal, as certain scenes could benefit more from specific viewpoints. To address this limitation, we propose a novel active viewpoint selection strategy. This strategy predicts images from unknown viewpoints based on information from observation images for each scene. It then compares the object-centric representations extracted from both viewpoints and selects the unknown viewpoint with the largest disparity, indicating the greatest gain in information, as the next observation viewpoint. Through experiments on various datasets, we demonstrate the effectiveness of our active viewpoint selection strategy, significantly enhancing segmentation and reconstruction performance compared to random viewpoint selection. Moreover, our method can accurately predict images from unknown viewpoints. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLatrieval: LLM-Verified Retrieval for Verifiable Generation

LLatrieval: LLM-Verified Retrieval for Verifiable Generation

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Li, Xiaonan Zhu, Changtai Li, Linyang Yin, Zhangyue Sun, Tianxiang Qiu, Xipeng School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9798891761148

Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM’s output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM’s output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferior to LLMs since they often have much fewer parameters than the large language model and have not been demonstrated to scale well to the size of LLMs. If the retriever does not correctly find the supporting documents, the LLM can not generate the correct and verifiable answer, which overshadows the LLM’s remarkable abilities. To address these limitations, we propose LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Thus, the LLM can iteratively provide feedback to retrieval and facilitate the retrieval result to fully support verifiable generation. Experiments on ALCE show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：