检索结果-内蒙古大学图书馆

Learning discriminative foreground-and-background features for few-shot segmentation

Multimedia Tools and Applications 2024年第18期83卷 55999-56019页

作者： Jiang, Cong Zhou, Yange Liu, Zhaoshuo Feng, Chaolu Li, Wei Yang, Jinzhu School of Computer Science and Engineering Northeastern University Liaoning Shenyang110819 China College of Science Northeastern University Liaoning Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Liaoning Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang110819 China

Few-shot Semantic Segmentation (FSS) endeavors to segment novel categories in a query image by referring to a support set comprising only a few annotated examples. Presently, many existing FSS methodologies primarily embrace the prototype learning paradigm and concentrate on optimizing the matching mechanism. However, these approaches tend to overlook the discrimination between the features of foreground background. Consequently, the segmentation results are often imprecise when it comes to capturing intricate structures, such as boundaries and small objects. In this study, we introduce the Discriminative Foreground-and-Background feature learning Network (DFBNet) to enhance the distinguishability of bilateral features. DFBNet comprises three major modules: a multi-level self-matching module (MSM), a feature separation module (FSM), and a semantic alignment module (SAM). The MSM generates prior masks separately for the foreground and background, employing a self-matching strategy across different feature levels. These prior masks are subsequently used as scaling factors within the FSM, where the features of the query’s foreground and background are independently scaled up and then concatenated along the channel dimension. Furthermore, we incorporate a two-layer Transformer encoder-based semantic alignment module (SAM) in DFBNet to refine the features, thereby creating a greater distinction between the foreground and background features. The performance of DFBNet is evaluated on the PASCAL-5i and COCO-20i benchmarks, demonstrating its superiority over existing solutions and establishing new state-of-the-art results in the field of few-shot semantic segmentation. The codes will be released if this paper is accepted. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

BEVTransFusion: LiDAR-Camera Fusion Under Bird’s-Eye-View for 3D Object Detection with Transformers

BEVTransFusion: LiDAR-Camera Fusion Under Bird’s-Eye-View f...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Kaiqi Feng Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province College of Control Science and Engineering Zhejiang University Hangzhou China

Recently, there is growing research interest in extracting Bird’s-Eye-View (BEV) features from images and LiDAR to improve 3D object detection. However, existing methods mainly combine the features mechanically, which limits the utilization of BEV features. To address this limitation, we draw inspiration from TransFusion and design a two-layer transformer decoder to fuse LiDAR and camera BEV features. By doing so, we can omit the steps of reference point backprojection and feature sampling, which results in better correlation between the fused LiDAR and image features and higher robustness to the calibration matrix. Furthermore, we add 3D position encoding to the BEV features to compensate for the lack of height information. We also propose an length-width-height modulated attention mechanism to incorporate scale information. We also perform comprehensive experiments to verify the effectiveness of our methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Triboelectric-electromagnetic hybrid generator with swing-blade structures for effectively harvesting distributed wind energy in urban environments

引用

Nano Research 2023年第9期16卷 11621-11629页

作者： Yangyang Yan Jinzhi Zhu Yuejun Zhang Zhaohui Wang Lin Jiang Zhong Lin Wang Jianyang Zhu Tinghai Cheng Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and TechnologyWuhan 430081China Beijing Institute of Nanoenergy and Nanosystems Chinese Academy of SciencesBeijing 101400China Georgia Institute of Technology AtlantaGA 30332-0245USA Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China

The wind energy in cities cannot be exploited effectively because natural wind is unstable and ***,a triboelectricelectromagnetic hybrid generator with swing-blade structures(SBS-TEHG)was designed to effectively harvest intermittent and continuous wind energy in an urban ***,the spring structure and base were considered to realize the maximum output performance of triboelectric ***,the computational fluid dynamics method was applied to optimize the structure of the SBS-TEHG to improve its aerodynamic *** starting wind speed of the SBS-TEHG was 2 m/s,and its energy conversion efficiency was 9.04%,159%higher than that of the SBS-TEHG without guide plates at 4 m/*** results demonstrated that the SBS-TEHG lit 105 light-emitting diodes(LEDs)under the intermittent-wind harvesting mode at a wind frequency of 1 Hz when the single swing blade operated,while a wireless PM_(2.5)&PM_(10)sensor was powered by the SBS-TEHG after a period of operation under the continuous-wind harvesting *** findings of this study provide a novel solution for lowspeed wind energy harvesting in cities and demonstrate the potential of SBS-TEHG as a distributed energy source.

关键词： triboelectric nanogenerator swing-blade structure low-speed wind energy computational fluid dynamics distributed energy source

来源：评论

学校读者我要写书评

暂无评论

Bis-benzylisoquinoline alkaloids inhibit flavivirus entry and replication by compromising endolysosomal trafficking and autophagy

引用

Virologica Sinica 2024年第6期39卷 892-908页

作者： Lihong Huang Lele Liu Junhai Zhu Nanjun Chen Jie Chen Chuen-Fuk Chan Fei Gao Youqin Yin Jiufeng Sun Rongxin Zhang Kehui Zhang Wenbao Qi Jianbo Yue State Key Laboratory for Animal Disease Control and Prevention South China Agricultural UniversityGuangzhou510642China Key Laboratory of Zoonoses Ministry of Agriculture and Rural AffairsSouth China Agricultural UniversityGuangzhou510642China National and Regional Joint Engineering Laboratory for Medicament of Zoonoses Prevention and Control Guangzhou510642China Key Laboratory of Zoonoses Prevention and Control of Guangdong Province GuangzhouChina Department of Computer Science City University of Hong KongHong Kong999077China Department of Biomedical Sciences City University of Hong KongHong Kong999077China Guangdong Workstation for Emerging Infectious Disease Control and Prevention Guangdong Provincial Key Laboratory of Pathogen Detection for Emerging Infectious Disease ResponseGuangdong Provincial Center for Disease Control and PreventionGuangzhou511430China Laboratory of Immunology and Inflammation Institute of Basic Medical Sciences and Department of BiotechnologySchool of Life Sciences and BiopharmaceuticsGuangdong Pharmaceutical UniversityGuangzhou510006China State Key Laboratory of Bioactive Substance and Function of Natural Medicines Institute of Materia MedicaChinese Academy of Medical Sciences&Peking Union Medical CollegeBeijing100730China Beijing Key Laboratory of Active Substances Discovery and Druggability Evaluation Institute of Materia MedicaChinese Academy of Medical Sciences&Peking Union Medical CollegeBeijing100730China City University of Hong Kong Shenzhen Research Institute Shenzhen518057China Division of Natural and Applied Sciences Synear Molecular Biology LabGlobal Health Research CenterDuke Kunshan UniversityKunshan215316China College of Life Sciences Wuhan UniversityWuhan430072China

Flaviviruses,such as dengue virus(DENV),Zika virus(ZIKV),and Japanese encephalitis virus(JEV),represent a substantial public health challenge as there are currently no approved treatments ***,we investigated the antiviral effects of bis-benzylisoquinoline alkaloids(BBAs)on flavivirus *** evaluated five specific BBAs—berbamine,tetrandrine,iso-tetrandrine,fangchinoline,and cepharanthine—and found that they effectively inhibited infections by ZIKV,DENV,or JEV by blocking virus entry and genome replication stages in the flavivirus life ***,we synthesized a fluorophore-conjugated BBA and showed that BBAs targeted endolysosomes,causing lysosomal pH *** studies on inhibiting ZIKV infection by BBAs revealed that these compounds blocked TRPML channels,leading to lysosomal dysfunction and reducing the expression of NCAM1,a key receptor for the entry of ZIKV into cells,thereby decreasing cells susceptibility to ZIKV ***,BBAs inhibited the fusion of autophagosomes and lysosomes,significantly reducing viral RNA ***,our results suggest that BBAs inhibit flavivirus entry and replication by compromising endolysosomal trafficking and autophagy,respectively,underscoring the potential of BBAs as therapeutic agents against flavivirus infections.

关键词： Bis-benzylisoquinoline alkaloids(BBAs) Flavivirus Zika virus(ZIKV) Endolysosomes TRPML channels Autophagy

来源：评论

学校读者我要写书评

暂无评论

SWITCH TO GENERALIZE: DOMAIN-SWITCH LEARNING FOR CROSS-DOMAIN FEW-SHOT CLASSIFICATION 10

SWITCH TO GENERALIZE: DOMAIN-SWITCH LEARNING FOR CROSS-DOMAI...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hu, Zhengdong Sun, Yifan Yang, Yi State Key Laboratory of Industrial Control Technology Zhejiang University China Baidu Research China CCAI College of Computer Science and Technology Zhejiang University China

This paper considers few-shot learning under the cross-domain scenario. The cross-domain setting imposes a critical challenge, i.e., using very few (support) samples to generalize the already-learned model to a novel domain. We hold a hypothesis, i.e., if a deep model is capable to fast generalize itself to different domains (using very few samples) during training, it will maintain such domain generalization capacity for testing. It motivates us to propose a novel Domain-Switch Learning (DSL) framework. DSL embeds the cross-domain scenario into the training stage in a "fast switching" manner. Specifically, DSL uses a single domain for a training iteration and switches into another domain for the following iteration. During the switching, DSL enforces two constraints: 1) the deep model should not over-fit the domain in the current iteration and 2) the deep model should not forget the already-learned knowledge of other domains. These two constraints jointly promote fast generalization across different domains. Experimental results confirm that the cross-domain generalization capacity can be inherited from the training stage to the testing stage, validating our key hypothesis. Consequentially, DSL significantly improves cross-domain few-shot classification and sets up new state of the art. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Monocular Biological Simultaneous Localization and Mapping Method Based on a Bionic Vision Model

A Monocular Biological Simultaneous Localization and Mapping...

引用

Frontiers of Robotics and Software engineering (FRSE), International Conference on

作者： Sitong Guo Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province Hangzhou China

Animals can navigate robustly through large unknown environments, utilizing inaccurate sensor and egomotion cues. Inspired by the mechanism of the human visual system, this paper presents a biological simultaneous localization and mapping (SLAM) system based on a monocular vision sensor to perform navigation tasks in complex environments. Specifically, our contributions are two folds: an improved monocular visual odometry with a scale recovery algorithm to calibrate the estimated robot pose, and a bionic vision model based on image enhancement algorithm and feature extraction approach to detect closed-loop. Experiments on public datasets demonstrate that our proposed method performs competitively in illumination-varying scenarios indoors and outdoors, which achieve a trade-off to maintain performances in terms of accuracy, execution time, and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Node Confidence Determination Based Moving Target Defense Strategy for SDN 15

A Node Confidence Determination Based Moving Target Defense ...

引用

15th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023

作者： Sun, Shimin Xu, Guowei Han, Li Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong Tianjin China Tianjin Univ. of Technol. Natl. Eng. Laboratory for Computer Virus Prevention and Control Technology School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350308693

With the rapid development of Internet technology, network assets have become an indispensable part of modern society. Especially in the face of high-value network assets, the attacker is faced with paying a greater cost to study the network structure. Due to the unknown attacker and attack means, the attacker has an advantage in the attack and defense situation. The moving target defense technique can flexibly change the static characteristics of the network attack surface and increase the difficulty for the attacker to detect the network, thus achieving the purpose of enhancing network security. Based on this technique, this paper proposes a defense strategy based on node confidence. It puts forward stricter constraints on the differential selection of address/port hopping paths, dynamically selects the hopping objects according to the node's confidence, and implements the defense strategy of differential complexity. This further increases the network's uncertainty and the difficulty for the attacker to detect the network structure. The experimental results show that in the path differentiation comparison, the maximum improvement is about 18% compared to the Dynamic Random Route Hopping strategy. In the CPU load experiment, the CPU load rate is reduced by about 4.625% on average compared to the Double Address Hopping strategy. Moreover, for larger hopping period, the proposed strategy also performs well in terms of CPU load rate. The proposed strategy also exhibits good performance in terms of CPU load ratio for large hopping cycles. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction 5

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fuzhou University College of Computer and Data Science Fuzhou China South China University of Technology School of Electronic and Information Engineering Guangzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350373820

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution

arXiv

引用

arXiv 2024年

作者： Zhuo, Yue Ge, Zhiqiang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

Feature attribution explains Artificial Intelligence (AI) at the instance level by providing importance scores of input features’ contributions to model prediction. Integrated Gradients (IG) is a prominent path attribution method for deep neural networks, involving the integration of gradients along a path from the explained input (explicand) to a counterfactual instance (baseline). Current IG variants primarily focus on the gradient of explicand’s output. However, our research indicates that the gradient of the counterfactual output significantly affects feature attribution as well. To achieve this, we propose Iterative Gradient path Integrated Gradients (IG2), considering both gradients. IG2 incorporates the counterfactual gradient iteratively into the integration path, generating a novel path (GradPath) and a novel baseline (GradCF). These two novel IG components effectively address the issues of attribution noise and arbitrary baseline choice in earlier IG methods. IG2, as a path method, satisfies many desirable axioms, which are theoretically justified in the paper. Experimental results on XAI benchmark, ImageNet, MNIST, TREC questions answering, wafer-map failure patterns, and CelebA face attributes validate that IG2 delivers superior feature attributions compared to the state-of-the-art techniques. The code is released at: https://***/JoeZhuo-ZY/IG2. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FedAWS: A Federated Tuning Approach with Adaptive Weight Shrinking for Pre-trained Foundation Models

FedAWS: A Federated Tuning Approach with Adaptive Weight Shr...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Yubin Cheng Zhihuan Song Xiaoyu Jiang Le Yao State Key Laboratory of Industrial Control Technology Institute of Industrial Process Control College of Control Science and Engineering Zhejiang University Hangzhou China School of Mathematics Hangzhou Normal University Hangzhou China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

In recent years, pre-trained foundation models have developed rapidly and have been applied to various downstream tasks through fine-tuning methods. However, due to the existence of data silos, the lack of data for fine-tuning has become a vital issue preventing the application of the foundation model to industry. In addition, the high complexity of the network makes the foundation model prone to overfitting when used for data-constrained industrial tasks. Therefore, a federated tuning approach with adaptive weight shrinking, named FedAWS, is proposed for collaborative fine-tuning between factories. FedAWS adaptively selects the weight-shrinking factor to reduce overfitting and improve the generalization of the global model without relying on additional data sets or human experience. The case study on an industrial dataset demonstrates the effectiveness of FedAWS. This successful validation provides a new way for inter-factory collaboration to apply the foundation model to industry, thus facilitating the efficient utilization of industrial data.

关键词： Industries Learning systems Adaptation models Collaboration control systems Data models Production facilities

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：